Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.5583. Min Act: -0.1700
Data Index: 3994676 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.3708. Min Act: -0.1700
Data Index: 3155854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 1676643 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 8746452 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 1676642 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 7439891 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 5136066 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 3472900 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.0583. Min Act: -0.1700
Data Index: 7935966 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.1208. Min Act: -0.1700
Data Index: 5729620 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9333. Min Act: -0.1700
Data Index: 5409599 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 4996608 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5583. Min Range: -9.5583
Max Act: 9.0583. Min Act: -0.1700
Data Index: 1818058 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 4666410 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 3807006 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 2188945 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9333. Min Act: -0.1700
Data Index: 6497566 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9333. Min Act: -0.1700
Data Index: 3719310 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 6177837 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5583. Min Range: -9.5583
Max Act: 8.9958. Min Act: -0.1700
Data Index: 5852132 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19