Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2236. Min Range: -4.2236
Max Act: 4.2236. Min Act: -0.1700
Data Index: 3285078 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2236. Min Range: -4.2236
Max Act: 4.1298. Min Act: -0.1700
Data Index: 4631262 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.9735. Min Act: -0.1700
Data Index: 650532 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.8641. Min Act: -0.1700
Data Index: 4579627 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.8641. Min Act: -0.1700
Data Index: 8417344 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.8328. Min Act: -0.1700
Data Index: 1086910 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7859. Min Act: -0.1700
Data Index: 622148 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7859. Min Act: -0.1700
Data Index: 7133345 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7859. Min Act: -0.1700
Data Index: 7480766 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7859. Min Act: -0.1700
Data Index: 4908894 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7703. Min Act: -0.1700
Data Index: 2403444 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7546. Min Act: -0.1700
Data Index: 2323761 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7546. Min Act: -0.1700
Data Index: 15652 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7234. Min Act: -0.1700
Data Index: 6151644 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7390. Min Act: -0.1700
Data Index: 5379981 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7234. Min Act: -0.1700
Data Index: 6647260 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7390. Min Act: -0.1700
Data Index: 4087328 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7234. Min Act: -0.1700
Data Index: 5327266 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7077. Min Act: -0.1700
Data Index: 5280382 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2236. Min Range: -4.2236
Max Act: 3.7234. Min Act: -0.1700
Data Index: 1704681 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19