Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0417. Min Range: -7.0417
Max Act: 7.0417. Min Act: -0.1700
Data Index: 4642765 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0417. Min Range: -7.0417
Max Act: 7.0105. Min Act: -0.1700
Data Index: 1591543 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.9480. Min Act: -0.1700
Data Index: 5336759 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.8855. Min Act: -0.1700
Data Index: 4846363 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.8542. Min Act: -0.1700
Data Index: 5758945 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.8230. Min Act: -0.1700
Data Index: 952595 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.7917. Min Act: -0.1700
Data Index: 7845805 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.7605. Min Act: -0.1700
Data Index: 4864971 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.7917. Min Act: -0.1700
Data Index: 6542714 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.7292. Min Act: -0.1700
Data Index: 2248396 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.7292. Min Act: -0.1700
Data Index: 1452853 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.6355. Min Act: -0.1700
Data Index: 1856732 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.6980. Min Act: -0.1700
Data Index: 7783748 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.6042. Min Act: -0.1700
Data Index: 597111 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.6042. Min Act: -0.1700
Data Index: 2619680 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.5105. Min Act: -0.1700
Data Index: 4434242 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.5105. Min Act: -0.1700
Data Index: 378621 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.4792. Min Act: -0.1700
Data Index: 1588124 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.4480. Min Act: -0.1700
Data Index: 5547566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0417. Min Range: -7.0417
Max Act: 6.4792. Min Act: -0.1700
Data Index: 1735570 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19