Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1131 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0421. Min Range: -4.0421
Max Act: 4.0421. Min Act: -0.1700
Data Index: 5829010 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9796. Min Act: -0.1700
Data Index: 2914078 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9483. Min Act: -0.1700
Data Index: 5290965 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9483. Min Act: -0.1700
Data Index: 7989285 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9483. Min Act: -0.1700
Data Index: 739893 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9171. Min Act: -0.1700
Data Index: 6805311 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9171. Min Act: -0.1700
Data Index: 836213 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8858. Min Act: -0.1700
Data Index: 5829007 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3905860 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8545. Min Act: -0.1700
Data Index: 4443459 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8545. Min Act: -0.1700
Data Index: 1302688 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3973610 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 7864667 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 168357 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 527981 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 5181037 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 7647468 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4654051 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4373966 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7607. Min Act: -0.1700
Data Index: 2294615 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19