Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3868 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.9128. Min Act: -0.1700
Data Index: 5798063 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7566. Min Act: -0.1700
Data Index: 7582119 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7566. Min Act: -0.1700
Data Index: 5231925 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3039291 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6941. Min Act: -0.1700
Data Index: 3563419 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6628. Min Act: -0.1700
Data Index: 6933950 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6316. Min Act: -0.1700
Data Index: 7858762 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 5654263 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3715698 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 8707686 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 7174783 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3159856 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 3210455 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5378. Min Act: -0.1700
Data Index: 6488707 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5378. Min Act: -0.1700
Data Index: 396633 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5378. Min Act: -0.1700
Data Index: 137905 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5378. Min Act: -0.1700
Data Index: 8210372 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5066. Min Act: -0.1700
Data Index: 2430315 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5066. Min Act: -0.1700
Data Index: 1784751 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9128. Min Range: -6.9128
Max Act: 6.5066. Min Act: -0.1700
Data Index: 3263183 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19