Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.5895. Min Act: -0.1700
Data Index: 3460810 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.5270. Min Act: -0.1698
Data Index: 7731058 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.4645. Min Act: -0.1700
Data Index: 3495120 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.4645. Min Act: -0.1700
Data Index: 861333 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.4020. Min Act: -0.1700
Data Index: 2818048 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3707. Min Act: -0.1700
Data Index: 2663944 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 943601 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3395. Min Act: -0.1700
Data Index: 3480021 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 2060252 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 1550449 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 1978470 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1699
Data Index: 1913032 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 8037633 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 765588 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.2770. Min Act: -0.1700
Data Index: 2199939 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.2770. Min Act: -0.1700
Data Index: 1595995 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.2770. Min Act: -0.1694
Data Index: 7335543 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.3082. Min Act: -0.1700
Data Index: 7843845 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5679398 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5895. Min Range: -5.5895
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5060966 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19