Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.4230. Min Act: -0.1700
Data Index: 4326977 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.4230. Min Act: -0.1700
Data Index: 2701940 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.3605. Min Act: -0.1700
Data Index: 3255829 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.3293. Min Act: -0.1700
Data Index: 70159 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2980. Min Act: -0.1700
Data Index: 1210250 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2668. Min Act: -0.1700
Data Index: 3065395 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2355. Min Act: -0.1700
Data Index: 4375126 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2668. Min Act: -0.1700
Data Index: 5104012 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2043. Min Act: -0.1700
Data Index: 1779761 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2355. Min Act: -0.1700
Data Index: 5348868 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2043. Min Act: -0.1700
Data Index: 8829536 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2043. Min Act: -0.1700
Data Index: 4572431 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4017824 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1730. Min Act: -0.1700
Data Index: 6616975 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1730. Min Act: -0.1700
Data Index: 6828906 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1730. Min Act: -0.1700
Data Index: 5387907 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1730. Min Act: -0.1700
Data Index: 8058637 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2769605 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.2043. Min Act: -0.1700
Data Index: 7399231 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4230. Min Range: -4.4230
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2452992 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19