Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.8340. Min Act: -0.1700
Data Index: 4988166 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7558. Min Act: -0.1700
Data Index: 953558 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.7558. Min Act: -0.1700
Data Index: 6861526 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6776. Min Act: -0.1700
Data Index: 3086406 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6933. Min Act: -0.1700
Data Index: 7747564 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6620. Min Act: -0.1700
Data Index: 3415398 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6463. Min Act: -0.1700
Data Index: 4433035 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.6150. Min Act: -0.1700
Data Index: 3800745 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5994. Min Act: -0.1700
Data Index: 3583751 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5994. Min Act: -0.1700
Data Index: 3280606 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 8680116 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5994. Min Act: -0.1700
Data Index: 6036167 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5837. Min Act: -0.1700
Data Index: 285356 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5368. Min Act: -0.1700
Data Index: 8152865 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5681. Min Act: -0.1700
Data Index: 343373 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5681. Min Act: -0.1700
Data Index: 2599336 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5524. Min Act: -0.1700
Data Index: 3983572 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5524. Min Act: -0.1700
Data Index: 2255892 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5524. Min Act: -0.1700
Data Index: 4222604 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8340. Min Range: -3.8340
Max Act: 3.5368. Min Act: -0.1700
Data Index: 7050128 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19