Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3418. Min Range: -7.3418
Max Act: 7.3418. Min Act: -0.1700
Data Index: 7056265 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3418. Min Range: -7.3418
Max Act: 7.2480. Min Act: -0.1700
Data Index: 8419184 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3418. Min Range: -7.3418
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3061461 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3418. Min Range: -7.3418
Max Act: 7.0293. Min Act: -0.1700
Data Index: 4642267 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.9980. Min Act: -0.1700
Data Index: 5018297 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.9043. Min Act: -0.1700
Data Index: 4615721 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.8418. Min Act: -0.1700
Data Index: 5497704 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.7480. Min Act: -0.1700
Data Index: 8519327 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.7168. Min Act: -0.1700
Data Index: 3466880 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6855. Min Act: -0.1700
Data Index: 7320190 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6855. Min Act: -0.1700
Data Index: 85501 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6543. Min Act: -0.1700
Data Index: 7909051 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6230. Min Act: -0.1700
Data Index: 7974267 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6543. Min Act: -0.1700
Data Index: 2921805 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.5918. Min Act: -0.1700
Data Index: 1615433 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6230. Min Act: -0.1700
Data Index: 6553632 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.5605. Min Act: -0.1700
Data Index: 1194645 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.6230. Min Act: -0.1700
Data Index: 4469977 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.5605. Min Act: -0.1700
Data Index: 512149 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3418. Min Range: -7.3418
Max Act: 6.5293. Min Act: -0.1700
Data Index: 3041779 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19