Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.9383. Min Act: -0.1700
Data Index: 4550011 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.8133. Min Act: -0.1700
Data Index: 4135267 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.7508. Min Act: -0.1700
Data Index: 1080229 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.7195. Min Act: -0.1700
Data Index: 2097334 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.5633. Min Act: -0.1700
Data Index: 1749693 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.5633. Min Act: -0.1700
Data Index: 2941817 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.5320. Min Act: -0.1700
Data Index: 4806568 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2807269 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.4695. Min Act: -0.1700
Data Index: 83411 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.5320. Min Act: -0.1700
Data Index: 6506990 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.4070. Min Act: -0.1700
Data Index: 1269350 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.4070. Min Act: -0.1700
Data Index: 513452 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.4070. Min Act: -0.1700
Data Index: 4502020 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3758. Min Act: -0.1700
Data Index: 1826273 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3758. Min Act: -0.1700
Data Index: 6371095 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3445. Min Act: -0.1700
Data Index: 1934357 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3445. Min Act: -0.1700
Data Index: 6645776 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3133. Min Act: -0.1700
Data Index: 6821148 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3445. Min Act: -0.1700
Data Index: 6067280 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9383. Min Range: -5.9383
Max Act: 5.3133. Min Act: -0.1700
Data Index: 3097338 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19