Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.2140. Min Act: -0.1700
Data Index: 1848728 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.2140. Min Act: -0.1700
Data Index: 5074467 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.1828. Min Act: -0.1700
Data Index: 4648938 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7928937 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.1203. Min Act: -0.1700
Data Index: 5125261 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.1203. Min Act: -0.1700
Data Index: 3176707 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.1203. Min Act: -0.1700
Data Index: 1015735 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0578. Min Act: -0.1700
Data Index: 5308239 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 5827849 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 7052854 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 4369301 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 3176700 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 1813799 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 5074477 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0578. Min Act: -0.1700
Data Index: 7532225 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0578. Min Act: -0.1700
Data Index: 641664 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0578. Min Act: -0.1700
Data Index: 7709500 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3255444 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0265. Min Act: -0.1700
Data Index: 7240375 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2140. Min Range: -5.2140
Max Act: 5.0265. Min Act: -0.1700
Data Index: 1324886 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19