Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0417. Min Range: -6.0417
Max Act: 6.0417. Min Act: -0.1700
Data Index: 7453522 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.8542. Min Act: -0.1700
Data Index: 1019985 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.8855. Min Act: -0.1700
Data Index: 5680627 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.8230. Min Act: -0.1700
Data Index: 2546078 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.8230. Min Act: -0.1700
Data Index: 1352628 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6980. Min Act: -0.1700
Data Index: 3759702 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6980. Min Act: -0.1700
Data Index: 8520377 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6355. Min Act: -0.1700
Data Index: 1696050 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6042. Min Act: -0.1700
Data Index: 4602753 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6042. Min Act: -0.1700
Data Index: 1723209 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5730. Min Act: -0.1700
Data Index: 6936623 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6355. Min Act: -0.1700
Data Index: 850497 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6042. Min Act: -0.1700
Data Index: 7503961 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5730. Min Act: -0.1700
Data Index: 4787875 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.6042. Min Act: -0.1700
Data Index: 2273629 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5730. Min Act: -0.1700
Data Index: 5618734 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5417. Min Act: -0.1700
Data Index: 2019318 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5417. Min Act: -0.1700
Data Index: 5341686 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5417. Min Act: -0.1700
Data Index: 8049337 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0417. Min Range: -6.0417
Max Act: 5.5417. Min Act: -0.1700
Data Index: 579413 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19