Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.3097. Min Act: -0.1700
Data Index: 8317689 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.2784. Min Act: -0.1700
Data Index: 739496 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.1222. Min Act: -0.1700
Data Index: 716246 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.0909. Min Act: -0.1700
Data Index: 132955 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.0909. Min Act: -0.1700
Data Index: 1873166 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.0284. Min Act: -0.1700
Data Index: 6935556 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3097. Min Range: -4.3097
Max Act: 4.0284. Min Act: -0.1700
Data Index: 5797230 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9346. Min Act: -0.1700
Data Index: 4745467 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9659. Min Act: -0.1700
Data Index: 7915645 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9659. Min Act: -0.1700
Data Index: 4598334 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9346. Min Act: -0.1700
Data Index: 5436099 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9346. Min Act: -0.1700
Data Index: 6971789 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9033. Min Act: -0.1700
Data Index: 6955774 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9033. Min Act: -0.1700
Data Index: 2285629 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9033. Min Act: -0.1700
Data Index: 5567447 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.8877. Min Act: -0.1700
Data Index: 1962595 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.8877. Min Act: -0.1700
Data Index: 7236397 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.8564. Min Act: -0.1700
Data Index: 6829916 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.9033. Min Act: -0.1700
Data Index: 3212389 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3097. Min Range: -4.3097
Max Act: 3.8721. Min Act: -0.1700
Data Index: 7900348 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19