Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4212. Min Range: -6.4212
Max Act: 6.4212. Min Act: -0.1700
Data Index: 1985105 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4212. Min Range: -6.4212
Max Act: 6.2337. Min Act: -0.1700
Data Index: 126993 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4212. Min Range: -6.4212
Max Act: 6.1087. Min Act: -0.1700
Data Index: 2141806 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4212. Min Range: -6.4212
Max Act: 6.0149. Min Act: -0.1700
Data Index: 7681381 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.9524. Min Act: -0.1700
Data Index: 390218 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.9212. Min Act: -0.1700
Data Index: 489198 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.9212. Min Act: -0.1700
Data Index: 1962293 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.9212. Min Act: -0.1700
Data Index: 1867990 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8899. Min Act: -0.1700
Data Index: 626213 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8587. Min Act: -0.1700
Data Index: 3807940 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8899. Min Act: -0.1700
Data Index: 1540496 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8587. Min Act: -0.1700
Data Index: 6773890 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8587. Min Act: -0.1700
Data Index: 7536218 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7962. Min Act: -0.1700
Data Index: 4187405 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.8274. Min Act: -0.1700
Data Index: 5991922 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7649. Min Act: -0.1700
Data Index: 5919731 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7962. Min Act: -0.1700
Data Index: 5225130 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7649. Min Act: -0.1700
Data Index: 488446 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7962. Min Act: -0.1700
Data Index: 153039 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4212. Min Range: -6.4212
Max Act: 5.7649. Min Act: -0.1700
Data Index: 3012134 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19