Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 257 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 4427785 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8639. Min Act: -0.1700
Data Index: 2822009 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8327. Min Act: -0.1700
Data Index: 492362 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8014. Min Act: -0.1700
Data Index: 7015668 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 1088814 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 5018473 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 7838517 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7389. Min Act: -0.1700
Data Index: 8105503 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7389. Min Act: -0.1700
Data Index: 2191695 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7389. Min Act: -0.1700
Data Index: 3825675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 568103 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5860883 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5018475 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 4179920 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 381187 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 2409223 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 5210992 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 3238366 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 2217082 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 35996 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19