Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4964 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 6630020 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.3433. Min Act: -0.1700
Data Index: 392660 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.2496. Min Act: -0.1700
Data Index: 6168975 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.1246. Min Act: -0.1700
Data Index: 171286 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.1246. Min Act: -0.1700
Data Index: 1443816 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0933. Min Act: -0.1700
Data Index: 7159213 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0933. Min Act: -0.1700
Data Index: 1629516 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 768987 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 1859858 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 7089732 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 3603658 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9996. Min Act: -0.1700
Data Index: 1209569 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8121. Min Range: -5.8121
Max Act: 5.0308. Min Act: -0.1700
Data Index: 7089731 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 5218709 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9996. Min Act: -0.1700
Data Index: 7263253 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4881559 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 6629780 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4881547 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9058. Min Act: -0.1699
Data Index: 1445010 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8121. Min Range: -5.8121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 7669821 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19