Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0165. Min Range: -5.0165
Max Act: 5.0165. Min Act: -0.1700
Data Index: 7649 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.8290. Min Act: -0.1700
Data Index: 3178130 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.8602. Min Act: -0.1700
Data Index: 474081 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.8602. Min Act: -0.1700
Data Index: 754694 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.8602. Min Act: -0.1700
Data Index: 2371381 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.8290. Min Act: -0.1700
Data Index: 5608041 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7977. Min Act: -0.1700
Data Index: 3665467 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 971996 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 4995357 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 6817576 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 2374361 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 2277160 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 705715 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1348378 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7352. Min Act: -0.1700
Data Index: 5452974 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7352. Min Act: -0.1700
Data Index: 2294484 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7040. Min Act: -0.1700
Data Index: 4219261 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7040. Min Act: -0.1700
Data Index: 201512 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.7040. Min Act: -0.1699
Data Index: 7639309 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0165. Min Range: -5.0165
Max Act: 4.6727. Min Act: -0.1700
Data Index: 754693 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19