Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.9602. Min Act: -0.1700
Data Index: 196986 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.8352. Min Act: -0.1700
Data Index: 8350575 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.6789. Min Act: -0.1700
Data Index: 8536598 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.4914. Min Act: -0.1700
Data Index: 4798182 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.4602. Min Act: -0.1700
Data Index: 5881149 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.4602. Min Act: -0.1700
Data Index: 1891842 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.4289. Min Act: -0.1700
Data Index: 4446028 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.4289. Min Act: -0.1700
Data Index: 5171341 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3977. Min Act: -0.1700
Data Index: 1528392 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3977. Min Act: -0.1700
Data Index: 6861597 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3977. Min Act: -0.1700
Data Index: 4983731 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3352. Min Act: -0.1700
Data Index: 121867 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3664. Min Act: -0.1700
Data Index: 7190675 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3664. Min Act: -0.1700
Data Index: 4432356 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3664. Min Act: -0.1700
Data Index: 6424801 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3664. Min Act: -0.1700
Data Index: 1108871 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3352. Min Act: -0.1700
Data Index: 2728092 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3352. Min Act: -0.1700
Data Index: 7864446 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3039. Min Act: -0.1700
Data Index: 3430767 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9602. Min Range: -6.9602
Max Act: 6.3039. Min Act: -0.1700
Data Index: 5502185 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19