Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5730. Min Range: -10.5730
Max Act: 10.5730. Min Act: -0.1700
Data Index: 8444855 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5730. Min Range: -10.5730
Max Act: 10.3855. Min Act: -0.1700
Data Index: 7392848 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5730. Min Range: -10.5730
Max Act: 10.1355. Min Act: -0.1700
Data Index: 4925764 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.9480. Min Act: -0.1700
Data Index: 4124581 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.8230. Min Act: -0.1700
Data Index: 4320268 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6980. Min Act: -0.1700
Data Index: 8085922 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.7605. Min Act: -0.1700
Data Index: 4733522 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.7605. Min Act: -0.1700
Data Index: 4094291 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6980. Min Act: -0.1700
Data Index: 1481272 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6980. Min Act: -0.1700
Data Index: 5334906 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6980. Min Act: -0.1700
Data Index: 5170338 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.5730. Min Act: -0.1700
Data Index: 5195231 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6355. Min Act: -0.1700
Data Index: 106691 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.5730. Min Act: -0.1700
Data Index: 45673 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6355. Min Act: -0.1700
Data Index: 3009570 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6355. Min Act: -0.1700
Data Index: 7598323 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6355. Min Act: -0.1700
Data Index: 5338392 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.6355. Min Act: -0.1700
Data Index: 4242651 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.5730. Min Act: -0.1700
Data Index: 3099266 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5730. Min Range: -10.5730
Max Act: 9.5730. Min Act: -0.1700
Data Index: 4046999 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19