Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.3901. Min Act: -0.1700
Data Index: 7706331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2964. Min Act: -0.1700
Data Index: 4145390 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2964. Min Act: -0.1700
Data Index: 7731804 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2964. Min Act: -0.1700
Data Index: 3125339 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 2933930 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 3033428 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2964. Min Act: -0.1700
Data Index: 6268870 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 6253245 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 5606784 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1248140 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 1979079 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 6077372 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 8430861 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1148539 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 7046120 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 1425751 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2026. Min Act: -0.1700
Data Index: 410371 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2026. Min Act: -0.1700
Data Index: 4013312 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2026. Min Act: -0.1700
Data Index: 6945275 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2026. Min Act: -0.1700
Data Index: 4120427 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19