Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3100 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.9072. Min Act: -0.0001
Data Index: 42858 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.7366. Min Act: -0.0001
Data Index: 188751 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.7947. Min Act: -0.0001
Data Index: 285242 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.6275. Min Act: -0.0001
Data Index: 259577 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.6866. Min Act: -0.0001
Data Index: 1116758 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.7451. Min Act: -0.0001
Data Index: 464268 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.6987. Min Act: -0.0001
Data Index: 460727 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.6234. Min Act: -0.0001
Data Index: 1131802 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.6223. Min Act: -0.0001
Data Index: 31394 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.5865. Min Act: -0.0001
Data Index: 1135927 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.5655. Min Act: -0.0001
Data Index: 1219764 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.5747. Min Act: -0.0001
Data Index: 116080 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.4567. Min Act: -0.0001
Data Index: 331175 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.4326. Min Act: -0.0001
Data Index: 710919 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.5089. Min Act: -0.0001
Data Index: 1358144 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.4245. Min Act: -0.0001
Data Index: 1314599 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.4665. Min Act: -0.0001
Data Index: 1214737 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.3760. Min Act: -0.0001
Data Index: 742235 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.3765. Min Act: -0.0001
Data Index: 1048130 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9072. Min Range: -1.9072
Max Act: 1.4589. Min Act: -0.0001
Data Index: 220194 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19