Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3324. Min Range: -6.3324
Max Act: 6.3324. Min Act: -0.1700
Data Index: 6691832 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3324. Min Range: -6.3324
Max Act: 6.1136. Min Act: -0.1700
Data Index: 6887006 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3324. Min Range: -6.3324
Max Act: 6.0824. Min Act: -0.1700
Data Index: 5222265 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3324. Min Range: -6.3324
Max Act: 6.0199. Min Act: -0.1700
Data Index: 1727410 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8949. Min Act: -0.1700
Data Index: 7121526 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8636. Min Act: -0.1700
Data Index: 5282045 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8011. Min Act: -0.1700
Data Index: 6406685 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8324. Min Act: -0.1700
Data Index: 3139378 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8324. Min Act: -0.1700
Data Index: 143072 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8011. Min Act: -0.1700
Data Index: 6078440 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8011. Min Act: -0.1700
Data Index: 1727416 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7699. Min Act: -0.1700
Data Index: 5602881 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7120368 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7386. Min Act: -0.1700
Data Index: 4410667 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7074. Min Act: -0.1700
Data Index: 3339492 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7074. Min Act: -0.1700
Data Index: 1322863 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7074. Min Act: -0.1700
Data Index: 1923008 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7074. Min Act: -0.1700
Data Index: 6317120 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.7074. Min Act: -0.1700
Data Index: 3105299 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3324. Min Range: -6.3324
Max Act: 5.6761. Min Act: -0.1700
Data Index: 1727421 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19