Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.4846. Min Act: -0.1700
Data Index: 1240783 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.4221. Min Act: -0.1700
Data Index: 1654371 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.3596. Min Act: -0.1700
Data Index: 5702072 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.2346. Min Act: -0.1700
Data Index: 7949694 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.2971. Min Act: -0.1700
Data Index: 2789119 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.2346. Min Act: -0.1700
Data Index: 8576355 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 6727455 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 5940950 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 1587536 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 4667861 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 7898462 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 1840861 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 6454205 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 22739 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.0471. Min Act: -0.1700
Data Index: 8228379 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 2376876 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.1096. Min Act: -0.1700
Data Index: 3845055 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.0471. Min Act: -0.1700
Data Index: 4003260 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.0471. Min Act: -0.1700
Data Index: 3160753 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4846. Min Range: -8.4846
Max Act: 8.0471. Min Act: -0.1700
Data Index: 5438000 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19