Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.1815. Min Act: -0.1700
Data Index: 66860 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.1502. Min Act: -0.1700
Data Index: 1018292 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.1502. Min Act: -0.1700
Data Index: 4654811 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.1190. Min Act: -0.1700
Data Index: 1342952 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.0877. Min Act: -0.1700
Data Index: 7193907 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.0565. Min Act: -0.1700
Data Index: 3190033 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1815. Min Range: -5.1815
Max Act: 5.0252. Min Act: -0.1700
Data Index: 7423866 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9940. Min Act: -0.1700
Data Index: 3061341 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9940. Min Act: -0.1700
Data Index: 3591542 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9002. Min Act: -0.1700
Data Index: 150030 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7488642 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9002. Min Act: -0.1700
Data Index: 8420785 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9002. Min Act: -0.1700
Data Index: 5845623 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1927269 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.9315. Min Act: -0.1700
Data Index: 3449063 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7076306 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.8690. Min Act: -0.1700
Data Index: 2605373 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.8690. Min Act: -0.1700
Data Index: 4303659 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.8377. Min Act: -0.1700
Data Index: 4516424 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1815. Min Range: -5.1815
Max Act: 4.8377. Min Act: -0.1700
Data Index: 7440981 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19