Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4310 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1518. Min Range: -7.1518
Max Act: 7.1518. Min Act: -0.1700
Data Index: 256060 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1518. Min Range: -7.1518
Max Act: 7.0580. Min Act: -0.1700
Data Index: 929714 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.9330. Min Act: -0.1700
Data Index: 7130871 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.7455. Min Act: -0.1700
Data Index: 1057477 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.7143. Min Act: -0.1700
Data Index: 8532663 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.6830. Min Act: -0.1700
Data Index: 810651 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.6518. Min Act: -0.1700
Data Index: 8409973 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.6518. Min Act: -0.1700
Data Index: 4335996 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 1914912 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 3280670 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5268. Min Act: -0.1700
Data Index: 5339102 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5268. Min Act: -0.1700
Data Index: 169670 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 2684290 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 6720789 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 6937278 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5580. Min Act: -0.1700
Data Index: 3803034 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5268. Min Act: -0.1700
Data Index: 5912984 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.4955. Min Act: -0.1700
Data Index: 5884334 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.4955. Min Act: -0.1700
Data Index: 2752539 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1518. Min Range: -7.1518
Max Act: 6.5268. Min Act: -0.1700
Data Index: 550672 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19