Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2535 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1235. Min Range: -4.1235

Max Act: 4.0742. Min Act: -0.0000

Data Index: 1156779 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 4.1235. Min Range: -4.1235

Max Act: 4.0209. Min Act: -0.0000

Data Index: 1252312 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.9899. Min Act: -0.0000

Data Index: 333914 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.8220. Min Act: -0.0000

Data Index: 1103309 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 4.1235. Min Range: -4.1235

Max Act: 4.1235. Min Act: -0.0000

Data Index: 562480 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6823. Min Act: -0.0000

Data Index: 106593 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.7854. Min Act: -0.0000

Data Index: 395805 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6724. Min Act: -0.0000

Data Index: 947341 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.8352. Min Act: -0.0000

Data Index: 1305705 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6690. Min Act: -0.0000

Data Index: 87804 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1336914 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.9621. Min Act: -0.0000

Data Index: 1029518 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6316. Min Act: -0.0000

Data Index: 157121 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.4465. Min Act: -0.0000

Data Index: 466024 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.4502. Min Act: -0.0000

Data Index: 941657 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.5738. Min Act: -0.0000

Data Index: 821974 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.5936. Min Act: -0.0000

Data Index: 661224 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.5311. Min Act: -0.0000

Data Index: 366817 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.5034. Min Act: -0.0000

Data Index: 425995 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 4.1235. Min Range: -4.1235

Max Act: 3.6507. Min Act: -0.0000

Data Index: 558237 (C4 (Web Text))

Max Activating Token Index: 378