Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3324. Min Range: -8.3324
Max Act: 8.3324. Min Act: -0.1700
Data Index: 5110247 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3324. Min Range: -8.3324
Max Act: 8.2699. Min Act: -0.1700
Data Index: 736548 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.8949. Min Act: -0.1700
Data Index: 2346124 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.8324. Min Act: -0.1700
Data Index: 7224552 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.8011. Min Act: -0.1700
Data Index: 7670175 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.7386. Min Act: -0.1700
Data Index: 6118673 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.7699. Min Act: -0.1700
Data Index: 877483 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.6449. Min Act: -0.1700
Data Index: 7299204 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.5511. Min Act: -0.1700
Data Index: 736553 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.5511. Min Act: -0.1700
Data Index: 6135532 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.5199. Min Act: -0.1700
Data Index: 7233094 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.5199. Min Act: -0.1700
Data Index: 6991324 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.4886. Min Act: -0.1700
Data Index: 7274182 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.4886. Min Act: -0.1700
Data Index: 4866681 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.4574. Min Act: -0.1700
Data Index: 6174821 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.4574. Min Act: -0.1700
Data Index: 1030919 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.4574. Min Act: -0.1700
Data Index: 4269827 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.3949. Min Act: -0.1700
Data Index: 4387264 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.3949. Min Act: -0.1700
Data Index: 5739780 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3324. Min Range: -8.3324
Max Act: 7.3949. Min Act: -0.1700
Data Index: 6848411 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19