Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5162 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1422. Min Range: -6.1422
Max Act: 6.1422. Min Act: -0.1700
Data Index: 1026112 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1422. Min Range: -6.1422
Max Act: 6.0797. Min Act: -0.1700
Data Index: 4370703 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1422. Min Range: -6.1422
Max Act: 6.0484. Min Act: -0.1700
Data Index: 5687125 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.9859. Min Act: -0.1700
Data Index: 1406163 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.9859. Min Act: -0.1700
Data Index: 1716439 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.9547. Min Act: -0.1700
Data Index: 6890433 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.9547. Min Act: -0.1700
Data Index: 6275859 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.9547. Min Act: -0.1700
Data Index: 3461396 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.8922. Min Act: -0.1700
Data Index: 5525959 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.8922. Min Act: -0.1700
Data Index: 888848 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.8922. Min Act: -0.1700
Data Index: 2447251 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.8609. Min Act: -0.1700
Data Index: 4522854 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.8297. Min Act: -0.1700
Data Index: 7946217 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7672. Min Act: -0.1700
Data Index: 1002963 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7359. Min Act: -0.1700
Data Index: 1496950 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7047. Min Act: -0.1700
Data Index: 2021741 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7047. Min Act: -0.1700
Data Index: 1148860 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7047. Min Act: -0.1700
Data Index: 2385808 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7359. Min Act: -0.1700
Data Index: 751579 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1422. Min Range: -6.1422
Max Act: 5.7047. Min Act: -0.1700
Data Index: 4504771 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19