Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1158887 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.7628. Min Act: -0.1700
Data Index: 4391416 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.7316. Min Act: -0.1700
Data Index: 1183817 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.7628. Min Act: -0.1700
Data Index: 6791687 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.6691. Min Act: -0.1700
Data Index: 5070422 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.5753. Min Act: -0.1700
Data Index: 3832723 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.5441. Min Act: -0.1700
Data Index: 6595782 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.4191. Min Act: -0.1700
Data Index: 214825 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.4191. Min Act: -0.1700
Data Index: 3915530 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.3878. Min Act: -0.1700
Data Index: 1987771 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.3566. Min Act: -0.1700
Data Index: 7043713 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.3566. Min Act: -0.1700
Data Index: 3612387 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.3253. Min Act: -0.1700
Data Index: 4642281 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.3253. Min Act: -0.1700
Data Index: 567831 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2941. Min Act: -0.1700
Data Index: 886676 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2941. Min Act: -0.1700
Data Index: 8661968 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2941. Min Act: -0.1700
Data Index: 8349956 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2941. Min Act: -0.1700
Data Index: 7253978 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2941. Min Act: -0.1700
Data Index: 3204367 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8878. Min Range: -5.8878
Max Act: 5.2628. Min Act: -0.1700
Data Index: 6963693 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19