Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.8398. Min Act: -0.1700
Data Index: 8650122 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7761. Min Act: -0.1700
Data Index: 4785701 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7442. Min Act: -0.1700
Data Index: 4238025 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7282. Min Act: -0.1700
Data Index: 3864908 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7282. Min Act: -0.1700
Data Index: 5971114 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7122. Min Act: -0.1700
Data Index: 3443450 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7282. Min Act: -0.1700
Data Index: 1694685 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7122. Min Act: -0.1700
Data Index: 4216589 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7122. Min Act: -0.1700
Data Index: 6345985 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6802. Min Act: -0.1700
Data Index: 7699628 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6962. Min Act: -0.1700
Data Index: 3960635 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.7122. Min Act: -0.1700
Data Index: 6362636 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6802. Min Act: -0.1700
Data Index: 279970 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6802. Min Act: -0.1700
Data Index: 5054975 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6642. Min Act: -0.1700
Data Index: 5656644 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6802. Min Act: -0.1700
Data Index: 5348298 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6802. Min Act: -0.1700
Data Index: 1713704 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6481. Min Act: -0.1700
Data Index: 3818429 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6321. Min Act: -0.1700
Data Index: 343553 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8398. Min Range: -2.8398
Max Act: 2.6642. Min Act: -0.1700
Data Index: 7611067 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19