Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.9539. Min Act: -0.1700
Data Index: 759803 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.9064. Min Act: -0.1700
Data Index: 6459667 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8905. Min Act: -0.1700
Data Index: 664819 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8746. Min Act: -0.1700
Data Index: 6535527 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8270. Min Act: -0.1700
Data Index: 7874880 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8587. Min Act: -0.1700
Data Index: 5434692 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8110. Min Act: -0.1700
Data Index: 940227 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8270. Min Act: -0.1700
Data Index: 8526998 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8270. Min Act: -0.1700
Data Index: 2964040 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8110. Min Act: -0.1700
Data Index: 5911291 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8110. Min Act: -0.1700
Data Index: 3955861 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8110. Min Act: -0.1700
Data Index: 7921162 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.8110. Min Act: -0.1700
Data Index: 4935793 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 4768452 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 5506504 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 8629160 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 5504691 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 1493153 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7951. Min Act: -0.1700
Data Index: 5338458 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9539. Min Range: -2.9539
Max Act: 2.7792. Min Act: -0.1700
Data Index: 43838 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19