Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.8126. Min Act: -0.1700
Data Index: 4958138 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.7189. Min Act: -0.1700
Data Index: 7423387 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7516369 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.6251. Min Act: -0.1700
Data Index: 7322039 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5939. Min Act: -0.1700
Data Index: 1930384 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5314. Min Act: -0.1700
Data Index: 1719659 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5001. Min Act: -0.1700
Data Index: 7687574 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4689. Min Act: -0.1700
Data Index: 8608907 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4689. Min Act: -0.1700
Data Index: 1581466 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4689. Min Act: -0.1700
Data Index: 2826320 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1774779 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 3195192 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1278910 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4064. Min Act: -0.1700
Data Index: 522993 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4064. Min Act: -0.1700
Data Index: 8513995 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4064. Min Act: -0.1700
Data Index: 3196627 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3439. Min Act: -0.1700
Data Index: 5225512 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 8432199 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 4802969 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3439. Min Act: -0.1700
Data Index: 6019593 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19