Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.7914. Min Act: -0.1700
Data Index: 915473 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.7602. Min Act: -0.1700
Data Index: 4896494 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.7602. Min Act: -0.1700
Data Index: 2154497 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.7289. Min Act: -0.1700
Data Index: 2754341 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6977. Min Act: -0.1700
Data Index: 6117984 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6977. Min Act: -0.1700
Data Index: 6742099 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6977. Min Act: -0.1700
Data Index: 7424636 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6977. Min Act: -0.1700
Data Index: 1543672 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6664. Min Act: -0.1700
Data Index: 859027 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6664. Min Act: -0.1700
Data Index: 7435057 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6664. Min Act: -0.1700
Data Index: 2983726 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6664. Min Act: -0.1700
Data Index: 7796176 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6352. Min Act: -0.1700
Data Index: 4373147 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6352. Min Act: -0.1700
Data Index: 6357713 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6352. Min Act: -0.1700
Data Index: 7796174 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6352. Min Act: -0.1700
Data Index: 6757645 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6039. Min Act: -0.1700
Data Index: 1092561 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6352. Min Act: -0.1700
Data Index: 7275345 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6039. Min Act: -0.1700
Data Index: 1177091 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7914. Min Range: -6.7914
Max Act: 6.6039. Min Act: -0.1700
Data Index: 5627633 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19