Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.8171. Min Act: -0.1700
Data Index: 5912286 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.6296. Min Act: -0.1700
Data Index: 4506836 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.5671. Min Act: -0.1700
Data Index: 4506834 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.5046. Min Act: -0.1700
Data Index: 7784683 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.4421. Min Act: -0.1700
Data Index: 3697760 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.4421. Min Act: -0.1700
Data Index: 5518341 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.4421. Min Act: -0.1700
Data Index: 3584365 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.2546. Min Act: -0.1700
Data Index: 5907840 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.1921. Min Act: -0.1700
Data Index: 4506840 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.1296. Min Act: -0.1700
Data Index: 7992367 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.0358. Min Act: -0.1700
Data Index: 6199292 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.0046. Min Act: -0.1700
Data Index: 8345119 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8171. Min Range: -8.8171
Max Act: 8.0046. Min Act: -0.1700
Data Index: 3087906 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.9421. Min Act: -0.1700
Data Index: 888792 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.9108. Min Act: -0.1700
Data Index: 8403929 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.8796. Min Act: -0.1700
Data Index: 6326799 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.8171. Min Act: -0.1700
Data Index: 4688830 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.8171. Min Act: -0.1700
Data Index: 5452158 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.7858. Min Act: -0.1700
Data Index: 6697342 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8171. Min Range: -8.8171
Max Act: 7.7858. Min Act: -0.1700
Data Index: 8148477 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19