Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.8890. Min Act: -0.1700
Data Index: 6443199 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.8890. Min Act: -0.1700
Data Index: 7749720 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.6390. Min Act: -0.1700
Data Index: 7064687 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.6077. Min Act: -0.1700
Data Index: 646473 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.5452. Min Act: -0.1700
Data Index: 4116534 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.5765. Min Act: -0.1700
Data Index: 722729 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.5452. Min Act: -0.1700
Data Index: 99272 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.4827. Min Act: -0.1700
Data Index: 2315285 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.4515. Min Act: -0.1700
Data Index: 4761237 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.4515. Min Act: -0.1700
Data Index: 2533940 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.4202. Min Act: -0.1700
Data Index: 1497352 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3890. Min Act: -0.1700
Data Index: 7444049 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3890. Min Act: -0.1700
Data Index: 4642552 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3577. Min Act: -0.1700
Data Index: 8226947 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3577. Min Act: -0.1700
Data Index: 8592575 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3577. Min Act: -0.1700
Data Index: 6426090 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.3265. Min Act: -0.1700
Data Index: 8128006 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.2952. Min Act: -0.1700
Data Index: 6600571 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.2640. Min Act: -0.1700
Data Index: 6728645 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8890. Min Range: -6.8890
Max Act: 6.2327. Min Act: -0.1700
Data Index: 4950473 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19