Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3868. Min Act: -0.1700
Data Index: 749510 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2931. Min Act: -0.1700
Data Index: 8110413 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 593949 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 7541115 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 63156 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2306. Min Act: -0.1700
Data Index: 5268791 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4399244 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2306. Min Act: -0.1700
Data Index: 5172069 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2306. Min Act: -0.1700
Data Index: 7147998 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2306. Min Act: -0.1700
Data Index: 3871227 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 7451242 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4307231 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2306. Min Act: -0.1700
Data Index: 4342246 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1681. Min Act: -0.1700
Data Index: 2129997 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1681. Min Act: -0.1700
Data Index: 8685275 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1993. Min Act: -0.1700
Data Index: 6379252 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1993. Min Act: -0.1700
Data Index: 8146284 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1681. Min Act: -0.1700
Data Index: 1436056 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1681. Min Act: -0.1700
Data Index: 1792822 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1681. Min Act: -0.1700
Data Index: 4306603 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19