Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.7232. Min Act: -0.1700
Data Index: 2170273 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6607. Min Act: -0.1700
Data Index: 119637 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 2170276 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.5982. Min Act: -0.1700
Data Index: 2170292 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6607. Min Act: -0.1700
Data Index: 2170296 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 2170278 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6294. Min Act: -0.1700
Data Index: 2170298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.5357. Min Act: -0.1700
Data Index: 4776875 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.6607. Min Act: -0.1700
Data Index: 7091069 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.4732. Min Act: -0.1700
Data Index: 4835654 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.5357. Min Act: -0.1700
Data Index: 981379 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5088281 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.4107. Min Act: -0.1700
Data Index: 6878378 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.3482. Min Act: -0.1700
Data Index: 1920786 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.3169. Min Act: -0.1700
Data Index: 320405 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.3169. Min Act: -0.1700
Data Index: 6975288 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.2857. Min Act: -0.1700
Data Index: 5934710 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3598108 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.2857. Min Act: -0.1700
Data Index: 4608916 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7232. Min Range: -6.7232
Max Act: 6.2857. Min Act: -0.1700
Data Index: 1736288 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19