Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 3468163 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 8318508 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.6062. Min Act: -0.1700
Data Index: 1028035 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.6062. Min Act: -0.1700
Data Index: 3808753 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 4068646 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 1711447 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4347525 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 6353336 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 6353338 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 6603842 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 1894991 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 8114178 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4186. Min Act: -0.1700
Data Index: 7598708 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4499. Min Act: -0.1700
Data Index: 4489808 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4499. Min Act: -0.1700
Data Index: 3491164 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4186. Min Act: -0.1700
Data Index: 2944406 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4186. Min Act: -0.1700
Data Index: 3594195 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4186. Min Act: -0.1700
Data Index: 7771637 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4186. Min Act: -0.1700
Data Index: 8035500 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.3874. Min Act: -0.1700
Data Index: 3993009 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19