Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.5180. Min Act: -0.1700
Data Index: 975270 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.3930. Min Act: -0.1700
Data Index: 1680285 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2680. Min Act: -0.1700
Data Index: 8219682 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2680. Min Act: -0.1700
Data Index: 3337039 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2680. Min Act: -0.1700
Data Index: 3656202 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.2367. Min Act: -0.1700
Data Index: 537422 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 5775424 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 1791513 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 3421902 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1742. Min Act: -0.1700
Data Index: 3789951 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1117. Min Act: -0.1700
Data Index: 8418776 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.1117. Min Act: -0.1700
Data Index: 7311860 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0804. Min Act: -0.1700
Data Index: 1871888 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0804. Min Act: -0.1700
Data Index: 1794227 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0492. Min Act: -0.1700
Data Index: 5013509 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0804. Min Act: -0.1700
Data Index: 5340709 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0179. Min Act: -0.1700
Data Index: 4928596 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0179. Min Act: -0.1700
Data Index: 8066764 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5180. Min Range: -4.5180
Max Act: 4.0179. Min Act: -0.1700
Data Index: 2646201 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5180. Min Range: -4.5180
Max Act: 3.9866. Min Act: -0.1700
Data Index: 6739923 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19