Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.4996. Min Act: -0.1700
Data Index: 7475255 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.2496. Min Act: -0.1700
Data Index: 4165853 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.2496. Min Act: -0.1700
Data Index: 5455040 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.1871. Min Act: -0.1700
Data Index: 3644413 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.1871. Min Act: -0.1700
Data Index: 1936808 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.1871. Min Act: -0.1700
Data Index: 2884294 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.1246. Min Act: -0.1700
Data Index: 347200 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4996. Min Range: -8.4996
Max Act: 8.0621. Min Act: -0.1700
Data Index: 6202744 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 5319768 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 4876530 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 6436474 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 6392079 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 6108384 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 1056532 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 146572 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9371. Min Act: -0.1700
Data Index: 2859351 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9371. Min Act: -0.1700
Data Index: 4128157 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9371. Min Act: -0.1700
Data Index: 6670829 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.8746. Min Act: -0.1700
Data Index: 5754718 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4996. Min Range: -8.4996
Max Act: 7.9371. Min Act: -0.1700
Data Index: 3505810 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19