Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.8311. Min Act: -0.1700
Data Index: 7048755 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.5811. Min Act: -0.1700
Data Index: 8112111 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.5811. Min Act: -0.1700
Data Index: 3356275 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.5186. Min Act: -0.1700
Data Index: 7516257 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.5186. Min Act: -0.1700
Data Index: 5293251 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.4561. Min Act: -0.1700
Data Index: 4372186 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.4248. Min Act: -0.1700
Data Index: 148990 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.4248. Min Act: -0.1700
Data Index: 13636 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3936. Min Act: -0.1700
Data Index: 6367485 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3936. Min Act: -0.1700
Data Index: 7655845 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3936. Min Act: -0.1700
Data Index: 1030259 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3936. Min Act: -0.1700
Data Index: 1348843 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3311. Min Act: -0.1700
Data Index: 5721523 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.3311. Min Act: -0.1700
Data Index: 2643363 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2998. Min Act: -0.1700
Data Index: 8410664 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2998. Min Act: -0.1700
Data Index: 3595902 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2686. Min Act: -0.1700
Data Index: 5147268 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2373. Min Act: -0.1700
Data Index: 3768996 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2686. Min Act: -0.1700
Data Index: 728784 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8311. Min Range: -6.8311
Max Act: 6.2373. Min Act: -0.1700
Data Index: 1551142 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19