Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.5216. Min Act: -0.1700
Data Index: 4648241 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.5041. Min Act: -0.1699
Data Index: 7032251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4865. Min Act: -0.1695
Data Index: 5965876 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.5041. Min Act: -0.1700
Data Index: 6108146 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4953. Min Act: -0.1700
Data Index: 413468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4865. Min Act: -0.1700
Data Index: 5652951 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4777. Min Act: -0.1700
Data Index: 2036558 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4602. Min Act: -0.1698
Data Index: 7818185 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4690. Min Act: -0.1696
Data Index: 957346 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4602. Min Act: -0.1699
Data Index: 3293540 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4602. Min Act: -0.1700
Data Index: 3630991 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4426. Min Act: -0.1700
Data Index: 8157919 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4514. Min Act: -0.1700
Data Index: 4917868 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4514. Min Act: -0.1700
Data Index: 8029090 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4426. Min Act: -0.1700
Data Index: 4515215 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4514. Min Act: -0.1700
Data Index: 1591146 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4426. Min Act: -0.1688
Data Index: 3855515 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4338. Min Act: -0.1681
Data Index: 7670424 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4338. Min Act: -0.1700
Data Index: 2651819 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5216. Min Range: -1.5216
Max Act: 1.4426. Min Act: -0.1697
Data Index: 6209544 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19