Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5886. Min Range: -8.5886
Max Act: 8.5886. Min Act: -0.1700
Data Index: 1435594 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5886. Min Range: -8.5886
Max Act: 8.3386. Min Act: -0.1700
Data Index: 4378951 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5886. Min Range: -8.5886
Max Act: 8.0886. Min Act: -0.1700
Data Index: 8377542 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5886. Min Range: -8.5886
Max Act: 8.0261. Min Act: -0.1700
Data Index: 6755503 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.9636. Min Act: -0.1700
Data Index: 6685867 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.9011. Min Act: -0.1700
Data Index: 2211179 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.9011. Min Act: -0.1700
Data Index: 7932541 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.7761. Min Act: -0.1700
Data Index: 4273743 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.8386. Min Act: -0.1700
Data Index: 298238 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.7136. Min Act: -0.1700
Data Index: 6121165 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.7136. Min Act: -0.1700
Data Index: 8619055 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6824. Min Act: -0.1700
Data Index: 3172015 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6824. Min Act: -0.1700
Data Index: 1512738 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6824. Min Act: -0.1700
Data Index: 8663764 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.7136. Min Act: -0.1700
Data Index: 3283246 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6824. Min Act: -0.1700
Data Index: 4752338 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6199. Min Act: -0.1700
Data Index: 1383427 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6199. Min Act: -0.1700
Data Index: 290004 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.6199. Min Act: -0.1700
Data Index: 5054505 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5886. Min Range: -8.5886
Max Act: 7.5886. Min Act: -0.1700
Data Index: 1083606 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19