Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.3714. Min Act: -0.1700
Data Index: 141329 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.3714. Min Act: -0.1700
Data Index: 3134729 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.3714. Min Act: -0.1700
Data Index: 7501148 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.2464. Min Act: -0.1700
Data Index: 2288119 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1839. Min Act: -0.1700
Data Index: 3049283 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1839. Min Act: -0.1700
Data Index: 8628485 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1527. Min Act: -0.1700
Data Index: 7247798 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1527. Min Act: -0.1700
Data Index: 5529378 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1527. Min Act: -0.1700
Data Index: 4706862 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1839. Min Act: -0.1700
Data Index: 2496486 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1214. Min Act: -0.1700
Data Index: 3021986 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1214. Min Act: -0.1700
Data Index: 4500804 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.1214. Min Act: -0.1700
Data Index: 1432292 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0902. Min Act: -0.1700
Data Index: 1426936 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0902. Min Act: -0.1700
Data Index: 1217397 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0902. Min Act: -0.1700
Data Index: 4987737 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0589. Min Act: -0.1700
Data Index: 4805998 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0589. Min Act: -0.1700
Data Index: 3326087 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0276. Min Act: -0.1700
Data Index: 847189 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3714. Min Range: -4.3714
Max Act: 4.0589. Min Act: -0.1700
Data Index: 58111 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19