Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0533. Min Range: -11.0533
Max Act: 11.0533. Min Act: -0.1700
Data Index: 2268190 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.8658. Min Act: -0.1700
Data Index: 3090690 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.8658. Min Act: -0.1700
Data Index: 3127658 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.7408. Min Act: -0.1700
Data Index: 6900882 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.5533. Min Act: -0.1700
Data Index: 1034279 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4908. Min Act: -0.1700
Data Index: 7266738 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4283. Min Act: -0.1700
Data Index: 1434018 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4283. Min Act: -0.1700
Data Index: 4855965 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4283. Min Act: -0.1700
Data Index: 4129430 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4283. Min Act: -0.1700
Data Index: 1441008 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.4283. Min Act: -0.1700
Data Index: 4395472 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3658. Min Act: -0.1700
Data Index: 8797998 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3658. Min Act: -0.1700
Data Index: 6900880 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3658. Min Act: -0.1700
Data Index: 7112147 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3033. Min Act: -0.1700
Data Index: 4993139 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3033. Min Act: -0.1700
Data Index: 4488171 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3033. Min Act: -0.1700
Data Index: 7112163 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.3033. Min Act: -0.1700
Data Index: 3168935 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.2408. Min Act: -0.1700
Data Index: 1687869 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0533. Min Range: -11.0533
Max Act: 10.1158. Min Act: -0.1700
Data Index: 2586510 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19