Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0970. Min Range: -6.0970
Max Act: 6.0970. Min Act: -0.1700
Data Index: 2787708 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.9095. Min Act: -0.1700
Data Index: 3740610 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.8470. Min Act: -0.1700
Data Index: 602362 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.8158. Min Act: -0.1700
Data Index: 3949903 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.7533. Min Act: -0.1700
Data Index: 3094767 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.7220. Min Act: -0.1700
Data Index: 968299 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6908. Min Act: -0.1700
Data Index: 619834 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3203238 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4979194 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6595. Min Act: -0.1700
Data Index: 6293079 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6595. Min Act: -0.1700
Data Index: 8147879 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6618397 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6595. Min Act: -0.1700
Data Index: 2824013 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6283. Min Act: -0.1700
Data Index: 1994151 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6283. Min Act: -0.1700
Data Index: 8319814 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6283. Min Act: -0.1700
Data Index: 841282 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.5970. Min Act: -0.1700
Data Index: 6821527 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6991676 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.5970. Min Act: -0.1700
Data Index: 3920394 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0970. Min Range: -6.0970
Max Act: 5.5970. Min Act: -0.1700
Data Index: 6002829 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19