Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.5110. Min Act: -0.1700
Data Index: 7982326 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4797. Min Act: -0.1700
Data Index: 1068343 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4640. Min Act: -0.1700
Data Index: 8281273 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4484. Min Act: -0.1700
Data Index: 8812556 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4327. Min Act: -0.1700
Data Index: 3330402 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4170. Min Act: -0.1700
Data Index: 2766274 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4013. Min Act: -0.1700
Data Index: 5425841 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4013. Min Act: -0.1700
Data Index: 7707735 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3857. Min Act: -0.1700
Data Index: 5087769 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.4013. Min Act: -0.1700
Data Index: 3235679 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3700. Min Act: -0.1700
Data Index: 4145331 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3857. Min Act: -0.1700
Data Index: 7078545 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3700. Min Act: -0.1700
Data Index: 7430646 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3543. Min Act: -0.1700
Data Index: 2181833 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3386. Min Act: -0.1700
Data Index: 806438 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3386. Min Act: -0.1700
Data Index: 7875669 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3072. Min Act: -0.1700
Data Index: 4834195 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3072. Min Act: -0.1700
Data Index: 7193188 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3072. Min Act: -0.1700
Data Index: 492641 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5110. Min Range: -3.5110
Max Act: 3.3072. Min Act: -0.1700
Data Index: 8619345 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19