Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.4529. Min Act: -0.1700
Data Index: 2530833 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.4529. Min Act: -0.1700
Data Index: 1002137 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3591. Min Act: -0.1700
Data Index: 5023785 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 4509526 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3904. Min Act: -0.1700
Data Index: 848760 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3279. Min Act: -0.1700
Data Index: 3032215 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3591. Min Act: -0.1700
Data Index: 6567794 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3279. Min Act: -0.1700
Data Index: 5045582 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3279. Min Act: -0.1699
Data Index: 5090744 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.3279. Min Act: -0.1700
Data Index: 3925487 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7162189 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 3709153 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 721077 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6172731 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 5399755 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 8823987 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 3190756 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 8746445 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2341. Min Act: -0.1700
Data Index: 1784694 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4529. Min Range: -5.4529
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4120231 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19