Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.8116. Min Act: -0.1700
Data Index: 7225685 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.4678. Min Act: -0.1700
Data Index: 5757707 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.3115. Min Act: -0.1693
Data Index: 1443524 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.2178. Min Act: -0.1699
Data Index: 4015118 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.2178. Min Act: -0.1700
Data Index: 5153753 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.1865. Min Act: -0.1700
Data Index: 3367673 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.1865. Min Act: -0.1700
Data Index: 1606632 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.1553. Min Act: -0.1700
Data Index: 2774641 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.1240. Min Act: -0.1685
Data Index: 6648679 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.1240. Min Act: -0.1697
Data Index: 5469014 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2774638 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0928. Min Act: -0.1692
Data Index: 7783043 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0928. Min Act: -0.1666
Data Index: 2774640 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0615. Min Act: -0.1698
Data Index: 7533336 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 7533350 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0615. Min Act: -0.1696
Data Index: 5153875 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 7087518 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0615. Min Act: -0.1680
Data Index: 2588830 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0928. Min Act: -0.1698
Data Index: 6648660 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8116. Min Range: -4.8116
Max Act: 4.0302. Min Act: -0.1700
Data Index: 1006974 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19