Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.5006. Min Act: -0.1700
Data Index: 7279503 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.4380. Min Act: -0.1700
Data Index: 4974062 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.4066. Min Act: -0.1700
Data Index: 6977599 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3752. Min Act: -0.1700
Data Index: 7881162 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3596. Min Act: -0.1700
Data Index: 3706725 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3596. Min Act: -0.1700
Data Index: 85330 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3439. Min Act: -0.1700
Data Index: 3461898 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3439. Min Act: -0.1700
Data Index: 4867204 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3282. Min Act: -0.1700
Data Index: 3553065 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3282. Min Act: -0.1700
Data Index: 8553356 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.3282. Min Act: -0.1700
Data Index: 5576976 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2968. Min Act: -0.1700
Data Index: 4819737 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2811. Min Act: -0.1700
Data Index: 7461554 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2968. Min Act: -0.1700
Data Index: 1205684 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2968. Min Act: -0.1700
Data Index: 2727829 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2654. Min Act: -0.1700
Data Index: 8564354 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2811. Min Act: -0.1700
Data Index: 6427198 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2811. Min Act: -0.1700
Data Index: 577944 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2811. Min Act: -0.1700
Data Index: 8815513 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5006. Min Range: -3.5006
Max Act: 3.2654. Min Act: -0.1700
Data Index: 4587106 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19