Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.8005. Min Act: -0.1700
Data Index: 7229294 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.7380. Min Act: -0.1700
Data Index: 4951302 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.7380. Min Act: -0.1700
Data Index: 3062183 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.6755. Min Act: -0.1700
Data Index: 8366454 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.5505. Min Act: -0.1700
Data Index: 6089782 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.6130. Min Act: -0.1700
Data Index: 3905905 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.5505. Min Act: -0.1700
Data Index: 3685793 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.5505. Min Act: -0.1700
Data Index: 3534914 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.5505. Min Act: -0.1700
Data Index: 1601188 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4880. Min Act: -0.1700
Data Index: 1424445 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 6036478 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 7637037 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 252263 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 7748116 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 7091606 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4880. Min Act: -0.1700
Data Index: 1896978 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.3630. Min Act: -0.1700
Data Index: 3398926 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.3630. Min Act: -0.1700
Data Index: 8531260 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 2071667 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8005. Min Range: -8.8005
Max Act: 8.3630. Min Act: -0.1700
Data Index: 8581710 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19