Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4956 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.1958. Min Act: -0.1700
Data Index: 8361001 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3232704 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3034932 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.0396. Min Act: -0.1700
Data Index: 2665696 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.0083. Min Act: -0.1700
Data Index: 5257376 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1958. Min Range: -6.1958
Max Act: 6.0083. Min Act: -0.1700
Data Index: 2476553 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.9771. Min Act: -0.1700
Data Index: 2043070 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.8833. Min Act: -0.1700
Data Index: 2829552 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.8208. Min Act: -0.1700
Data Index: 7546291 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.8208. Min Act: -0.1700
Data Index: 2651223 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1346660 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7896. Min Act: -0.1700
Data Index: 4471780 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7896. Min Act: -0.1700
Data Index: 6168396 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7896. Min Act: -0.1700
Data Index: 3605465 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7583. Min Act: -0.1700
Data Index: 3596245 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7583. Min Act: -0.1700
Data Index: 4471781 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7271. Min Act: -0.1700
Data Index: 2386141 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7271. Min Act: -0.1700
Data Index: 2782306 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7271. Min Act: -0.1700
Data Index: 2675048 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1958. Min Range: -6.1958
Max Act: 5.7271. Min Act: -0.1700
Data Index: 6414011 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19