Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.3873. Min Act: -0.1700
Data Index: 4848800 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.3873. Min Act: -0.1700
Data Index: 5909830 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.3560. Min Act: -0.1700
Data Index: 1215802 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.3248. Min Act: -0.1700
Data Index: 6468975 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.2935. Min Act: -0.1700
Data Index: 6541217 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.2935. Min Act: -0.1700
Data Index: 6242044 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.2623. Min Act: -0.1700
Data Index: 7606853 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.2310. Min Act: -0.1700
Data Index: 8798732 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.2310. Min Act: -0.1700
Data Index: 3240165 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1685. Min Act: -0.1700
Data Index: 8701988 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1685. Min Act: -0.1700
Data Index: 6341108 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1998. Min Act: -0.1700
Data Index: 2760960 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1060. Min Act: -0.1700
Data Index: 6187253 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.0748. Min Act: -0.1700
Data Index: 7218637 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1060. Min Act: -0.1700
Data Index: 3456964 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.1060. Min Act: -0.1700
Data Index: 1313544 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.0748. Min Act: -0.1700
Data Index: 3376675 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.0748. Min Act: -0.1700
Data Index: 3732512 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.0748. Min Act: -0.1700
Data Index: 5551177 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3873. Min Range: -6.3873
Max Act: 6.0435. Min Act: -0.1700
Data Index: 2370239 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19