Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.3552. Min Act: -0.1700
Data Index: 2305116 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.2927. Min Act: -0.1700
Data Index: 3352627 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.2614. Min Act: -0.1700
Data Index: 8366332 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.2302. Min Act: -0.1700
Data Index: 622412 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1364. Min Act: -0.1700
Data Index: 5482625 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1052. Min Act: -0.1700
Data Index: 6137052 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1052. Min Act: -0.1700
Data Index: 1629488 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0427. Min Act: -0.1700
Data Index: 2500387 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 8386058 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 6194716 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 593560 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 1180719 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2806625 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 107872 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 1450357 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 7461596 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9489. Min Act: -0.1700
Data Index: 1298028 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9177. Min Act: -0.1700
Data Index: 3569485 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2229932 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9489. Min Act: -0.1700
Data Index: 5211581 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19