Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1216. Min Range: -4.1216
Max Act: 4.1216. Min Act: -0.1700
Data Index: 8154751 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1216. Min Range: -4.1216
Max Act: 4.0591. Min Act: -0.1700
Data Index: 755520 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.9653. Min Act: -0.1700
Data Index: 7194920 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.9341. Min Act: -0.1700
Data Index: 3690895 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8715. Min Act: -0.1700
Data Index: 895225 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8715. Min Act: -0.1700
Data Index: 6382473 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8403. Min Act: -0.1700
Data Index: 4009260 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8403. Min Act: -0.1700
Data Index: 415445 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8403. Min Act: -0.1700
Data Index: 6554832 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8403. Min Act: -0.1700
Data Index: 5798208 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8715. Min Act: -0.1700
Data Index: 2463281 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8090. Min Act: -0.1700
Data Index: 6554829 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.8090. Min Act: -0.1700
Data Index: 2029906 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7464. Min Act: -0.1700
Data Index: 7981086 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7464. Min Act: -0.1700
Data Index: 4009262 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7464. Min Act: -0.1700
Data Index: 5798195 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7464. Min Act: -0.1700
Data Index: 4171196 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7464. Min Act: -0.1700
Data Index: 5143069 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.7152. Min Act: -0.1700
Data Index: 895220 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1216. Min Range: -4.1216
Max Act: 3.6839. Min Act: -0.1700
Data Index: 6554831 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19