Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5654 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.6111. Min Act: -0.1700
Data Index: 3498285 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.5173. Min Act: -0.1700
Data Index: 7199092 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.4548. Min Act: -0.1700
Data Index: 6692835 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.4236. Min Act: -0.1700
Data Index: 1103367 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.3923. Min Act: -0.1700
Data Index: 1958790 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.3923. Min Act: -0.1700
Data Index: 5743021 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.3923. Min Act: -0.1700
Data Index: 5818151 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.3611. Min Act: -0.1700
Data Index: 884226 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.3298. Min Act: -0.1700
Data Index: 8260987 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1690639 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2673. Min Act: -0.1700
Data Index: 6938981 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2673. Min Act: -0.1700
Data Index: 8260979 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2361. Min Act: -0.1700
Data Index: 3182401 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2361. Min Act: -0.1700
Data Index: 4055387 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2048. Min Act: -0.1700
Data Index: 5565145 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2048. Min Act: -0.1700
Data Index: 6594542 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.1736. Min Act: -0.1700
Data Index: 4095990 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.2048. Min Act: -0.1700
Data Index: 3237606 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.1736. Min Act: -0.1700
Data Index: 3290564 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6111. Min Range: -6.6111
Max Act: 6.1423. Min Act: -0.1700
Data Index: 5411909 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19