Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2433. Min Range: -5.2433
Max Act: 5.2433. Min Act: -0.1700
Data Index: 1180022 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2433. Min Range: -5.2433
Max Act: 5.0246. Min Act: -0.1700
Data Index: 1500089 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.9621. Min Act: -0.1700
Data Index: 6509766 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.8996. Min Act: -0.1700
Data Index: 3046266 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2204469 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.8371. Min Act: -0.1700
Data Index: 5304106 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7746. Min Act: -0.1700
Data Index: 666361 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7746. Min Act: -0.1700
Data Index: 4753613 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7746. Min Act: -0.1700
Data Index: 2432197 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 23327 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1513721 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 5142200 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 7361544 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 548638 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 5407865 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 4271911 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 6198941 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 2360903 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3842934 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2433. Min Range: -5.2433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 4112708 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19