Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.6739. Min Act: -0.1700
Data Index: 3624767 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.5489. Min Act: -0.1700
Data Index: 5554354 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.4864. Min Act: -0.1700
Data Index: 2574922 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.4239. Min Act: -0.1700
Data Index: 7183413 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.2989. Min Act: -0.1700
Data Index: 7841830 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.2364. Min Act: -0.1700
Data Index: 94374 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.1739. Min Act: -0.1700
Data Index: 2477328 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.1114. Min Act: -0.1700
Data Index: 6258794 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.1114. Min Act: -0.1700
Data Index: 8567395 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6739. Min Range: -8.6739
Max Act: 8.0489. Min Act: -0.1700
Data Index: 8655907 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.9864. Min Act: -0.1700
Data Index: 7840892 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.9864. Min Act: -0.1700
Data Index: 1350223 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.9864. Min Act: -0.1700
Data Index: 1493946 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.9552. Min Act: -0.1700
Data Index: 3267539 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.8927. Min Act: -0.1700
Data Index: 1246739 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.8614. Min Act: -0.1700
Data Index: 7351560 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.8614. Min Act: -0.1700
Data Index: 6429502 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.8614. Min Act: -0.1700
Data Index: 5886392 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.8302. Min Act: -0.1700
Data Index: 5449574 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6739. Min Range: -8.6739
Max Act: 7.7989. Min Act: -0.1700
Data Index: 5314954 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19