Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.4325. Min Act: -0.1700
Data Index: 7955393 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.4013. Min Act: -0.1700
Data Index: 2641437 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.3388. Min Act: -0.1700
Data Index: 820900 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4729 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.3388. Min Act: -0.1700
Data Index: 187288 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.3388. Min Act: -0.1700
Data Index: 7548464 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.2450. Min Act: -0.1700
Data Index: 4655905 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.2138. Min Act: -0.1700
Data Index: 1993415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1825. Min Act: -0.1700
Data Index: 8706931 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1825. Min Act: -0.1700
Data Index: 6185277 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1825. Min Act: -0.1700
Data Index: 5940929 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1513. Min Act: -0.1700
Data Index: 4599150 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1297768 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1513. Min Act: -0.1700
Data Index: 6058436 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1513. Min Act: -0.1700
Data Index: 2332868 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1200. Min Act: -0.1700
Data Index: 6788165 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1200. Min Act: -0.1700
Data Index: 6777331 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1513. Min Act: -0.1700
Data Index: 5023046 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.1200. Min Act: -0.1700
Data Index: 7560623 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4325. Min Range: -5.4325
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4228716 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19