Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.5632. Min Act: -0.1700
Data Index: 6769278 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.5632. Min Act: -0.1700
Data Index: 591835 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.3132. Min Act: -0.1700
Data Index: 8581789 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.3132. Min Act: -0.1700
Data Index: 6496625 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.2194. Min Act: -0.1700
Data Index: 973634 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.1569. Min Act: -0.1700
Data Index: 6686400 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.1569. Min Act: -0.1700
Data Index: 2248612 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.1569. Min Act: -0.1700
Data Index: 4470431 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.1257. Min Act: -0.1700
Data Index: 5634994 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0944. Min Act: -0.1700
Data Index: 470082 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0631. Min Act: -0.1700
Data Index: 7340888 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0319. Min Act: -0.1700
Data Index: 7950213 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0631. Min Act: -0.1700
Data Index: 7113559 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0631. Min Act: -0.1700
Data Index: 7986149 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0319. Min Act: -0.1700
Data Index: 3309681 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0319. Min Act: -0.1700
Data Index: 4036073 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0319. Min Act: -0.1700
Data Index: 367659 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0319. Min Act: -0.1700
Data Index: 7206876 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0631. Min Act: -0.1700
Data Index: 8127217 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5632. Min Range: -4.5632
Max Act: 4.0006. Min Act: -0.1700
Data Index: 1781339 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19