Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1181 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.2881. Min Act: -0.1700
Data Index: 5054423 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.2881. Min Act: -0.1700
Data Index: 394751 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.2569. Min Act: -0.1700
Data Index: 5505590 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.2256. Min Act: -0.1700
Data Index: 1581694 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.2256. Min Act: -0.1700
Data Index: 8704721 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1631. Min Act: -0.1700
Data Index: 1444268 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1631. Min Act: -0.1700
Data Index: 8435512 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1319. Min Act: -0.1700
Data Index: 3317525 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1006. Min Act: -0.1700
Data Index: 1730149 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1319. Min Act: -0.1700
Data Index: 75163 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1006. Min Act: -0.1700
Data Index: 8350184 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0694. Min Act: -0.1700
Data Index: 4613118 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1006. Min Act: -0.1700
Data Index: 357387 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.1006. Min Act: -0.1700
Data Index: 4982535 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0694. Min Act: -0.1700
Data Index: 3278997 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0694. Min Act: -0.1700
Data Index: 4902781 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0694. Min Act: -0.1700
Data Index: 1090521 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0381. Min Act: -0.1700
Data Index: 1552304 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0381. Min Act: -0.1700
Data Index: 5465267 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2881. Min Range: -4.2881
Max Act: 4.0694. Min Act: -0.1700
Data Index: 1516289 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19