Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4624 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.9964. Min Act: -0.1700
Data Index: 3018858 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.9339. Min Act: -0.1700
Data Index: 2485367 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.8714. Min Act: -0.1700
Data Index: 8422067 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.7463. Min Act: -0.1700
Data Index: 5925761 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.7463. Min Act: -0.1700
Data Index: 88312 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.7150. Min Act: -0.1700
Data Index: 2062463 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.7150. Min Act: -0.1700
Data Index: 3670064 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6837. Min Act: -0.1700
Data Index: 5723166 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6837. Min Act: -0.1700
Data Index: 4307247 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6837. Min Act: -0.1700
Data Index: 115031 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.7150. Min Act: -0.1700
Data Index: 1743702 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6524. Min Act: -0.1700
Data Index: 8089340 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6524. Min Act: -0.1700
Data Index: 7786745 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6837. Min Act: -0.1700
Data Index: 7172227 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6524. Min Act: -0.1700
Data Index: 8718919 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6211. Min Act: -0.1700
Data Index: 1485634 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6211. Min Act: -0.1700
Data Index: 2276951 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.6211. Min Act: -0.1700
Data Index: 2854261 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.5898. Min Act: -0.1700
Data Index: 3523409 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9964. Min Range: -3.9964
Max Act: 3.5898. Min Act: -0.1700
Data Index: 2489687 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19