Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4645 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.1802. Min Act: -0.1700
Data Index: 7937012 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.1802. Min Act: -0.1700
Data Index: 3242507 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.1177. Min Act: -0.1700
Data Index: 5423339 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.0552. Min Act: -0.1700
Data Index: 8669286 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.0552. Min Act: -0.1700
Data Index: 5185150 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1802. Min Range: -9.1802
Max Act: 9.0552. Min Act: -0.1700
Data Index: 2535821 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.9927. Min Act: -0.1700
Data Index: 7269920 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.9302. Min Act: -0.1700
Data Index: 5189707 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.9302. Min Act: -0.1700
Data Index: 2857574 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8677. Min Act: -0.1700
Data Index: 1112164 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8052. Min Act: -0.1700
Data Index: 831552 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8052. Min Act: -0.1700
Data Index: 1106329 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8052. Min Act: -0.1700
Data Index: 533224 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8052. Min Act: -0.1700
Data Index: 8049727 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.8052. Min Act: -0.1700
Data Index: 1793467 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.7427. Min Act: -0.1700
Data Index: 473448 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.6802. Min Act: -0.1700
Data Index: 4265330 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.7427. Min Act: -0.1700
Data Index: 3304760 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.7427. Min Act: -0.1700
Data Index: 301026 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1802. Min Range: -9.1802
Max Act: 8.7427. Min Act: -0.1700
Data Index: 1479413 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19