Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1226. Min Range: -5.1226
Max Act: 5.1226. Min Act: -0.1700
Data Index: 4396301 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1226. Min Range: -5.1226
Max Act: 5.0288. Min Act: -0.1700
Data Index: 108883 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1226. Min Range: -5.1226
Max Act: 5.0601. Min Act: -0.1700
Data Index: 4791965 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1226. Min Range: -5.1226
Max Act: 5.0288. Min Act: -0.1700
Data Index: 8765707 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9976. Min Act: -0.1700
Data Index: 2140118 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9663. Min Act: -0.1700
Data Index: 3830827 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9663. Min Act: -0.1700
Data Index: 230552 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9663. Min Act: -0.1700
Data Index: 6658075 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9663. Min Act: -0.1700
Data Index: 970536 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9976. Min Act: -0.1700
Data Index: 4660834 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9351. Min Act: -0.1700
Data Index: 3773854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9351. Min Act: -0.1700
Data Index: 7893772 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.8726. Min Act: -0.1700
Data Index: 975771 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1700
Data Index: 5683581 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1700
Data Index: 3787727 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1698
Data Index: 4292448 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1700
Data Index: 4795980 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1700
Data Index: 3764551 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1700
Data Index: 1751352 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1226. Min Range: -5.1226
Max Act: 4.9038. Min Act: -0.1694
Data Index: 3355255 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19