Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 4789755 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.4732. Min Act: -0.1700
Data Index: 6785147 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.3170. Min Act: -0.1700
Data Index: 8576217 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.2545. Min Act: -0.1700
Data Index: 6598520 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.2232. Min Act: -0.1700
Data Index: 3329239 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.1920. Min Act: -0.1700
Data Index: 7889889 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.1607. Min Act: -0.1700
Data Index: 1269140 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0982. Min Act: -0.1700
Data Index: 4278238 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0982. Min Act: -0.1700
Data Index: 556640 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.1295. Min Act: -0.1700
Data Index: 7581008 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0670. Min Act: -0.1700
Data Index: 5401211 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0670. Min Act: -0.1700
Data Index: 7078061 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0357. Min Act: -0.1700
Data Index: 7532347 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0357. Min Act: -0.1700
Data Index: 6641096 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5357. Min Range: -7.5357
Max Act: 7.0045. Min Act: -0.1700
Data Index: 5553898 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5357. Min Range: -7.5357
Max Act: 6.9732. Min Act: -0.1700
Data Index: 3003018 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5357. Min Range: -7.5357
Max Act: 6.9420. Min Act: -0.1700
Data Index: 2516254 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5357. Min Range: -7.5357
Max Act: 6.9420. Min Act: -0.1700
Data Index: 7762262 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5357. Min Range: -7.5357
Max Act: 6.9420. Min Act: -0.1700
Data Index: 255610 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5357. Min Range: -7.5357
Max Act: 6.9107. Min Act: -0.1700
Data Index: 8560269 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19