Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.6051. Min Act: -0.1700
Data Index: 2103783 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.4489. Min Act: -0.1700
Data Index: 7159065 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.4176. Min Act: -0.1700
Data Index: 2853061 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.3864. Min Act: -0.1700
Data Index: 3372506 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.3551. Min Act: -0.1700
Data Index: 2149409 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.2301. Min Act: -0.1700
Data Index: 2929795 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.1989. Min Act: -0.1700
Data Index: 1672113 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.1989. Min Act: -0.1700
Data Index: 2962019 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6051. Min Range: -7.6051
Max Act: 7.1051. Min Act: -0.1700
Data Index: 7940200 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.9801. Min Act: -0.1700
Data Index: 1291192 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.9801. Min Act: -0.1700
Data Index: 7994121 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.9489. Min Act: -0.1700
Data Index: 1834632 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 6321568 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 1160446 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 103076 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 3049471 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 1731754 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8864. Min Act: -0.1700
Data Index: 3174336 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 1320966 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6051. Min Range: -7.6051
Max Act: 6.8239. Min Act: -0.1700
Data Index: 5587596 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19