Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8453. Min Act: -0.1700
Data Index: 2614580 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8453. Min Act: -0.1700
Data Index: 6132993 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8609. Min Act: -0.1700
Data Index: 4175678 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8140. Min Act: -0.1700
Data Index: 4474970 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8140. Min Act: -0.1700
Data Index: 3162005 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7671. Min Act: -0.1700
Data Index: 6557409 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.8140. Min Act: -0.1700
Data Index: 446407 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7827. Min Act: -0.1700
Data Index: 1790043 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7827. Min Act: -0.1700
Data Index: 8422462 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7671. Min Act: -0.1700
Data Index: 89581 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7515. Min Act: -0.1700
Data Index: 7953401 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7358. Min Act: -0.1700
Data Index: 1007341 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7358. Min Act: -0.1700
Data Index: 7361326 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7202. Min Act: -0.1700
Data Index: 4737931 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7045. Min Act: -0.1700
Data Index: 2093852 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7202. Min Act: -0.1700
Data Index: 2903368 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7358. Min Act: -0.1700
Data Index: 1896520 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7202. Min Act: -0.1700
Data Index: 500951 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.6889. Min Act: -0.1700
Data Index: 3634642 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8609. Min Range: -3.8609
Max Act: 3.7045. Min Act: -0.1700
Data Index: 2083509 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19