Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.1802. Min Act: -0.1700
Data Index: 3784456 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.1177. Min Act: -0.1700
Data Index: 3390094 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.0552. Min Act: -0.1700
Data Index: 577824 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.0240. Min Act: -0.1700
Data Index: 4777662 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.0240. Min Act: -0.1700
Data Index: 226479 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1802. Min Range: -6.1802
Max Act: 6.0240. Min Act: -0.1700
Data Index: 3894317 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6164744 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8301255 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9615. Min Act: -0.1700
Data Index: 4426715 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9615. Min Act: -0.1700
Data Index: 7052902 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 4334864 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 5209746 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 8462949 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.9615. Min Act: -0.1700
Data Index: 505024 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8990. Min Act: -0.1700
Data Index: 7184490 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8677. Min Act: -0.1700
Data Index: 8527859 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8990. Min Act: -0.1700
Data Index: 4090085 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8677. Min Act: -0.1700
Data Index: 813600 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8990. Min Act: -0.1700
Data Index: 5787824 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1802. Min Range: -6.1802
Max Act: 5.8677. Min Act: -0.1700
Data Index: 4634774 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19