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

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

Neuron 2479 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: 1.4603. Min Range: -1.4603

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1248311 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3165. Min Act: -0.0000

Data Index: 586591 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1090631 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3371. Min Act: -0.0000

Data Index: 550250 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2212. Min Act: -0.0000

Data Index: 683951 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3005. Min Act: -0.0000

Data Index: 144417 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2066. Min Act: -0.0000

Data Index: 962085 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2007. Min Act: -0.0000

Data Index: 698717 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2456. Min Act: -0.0000

Data Index: 413373 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2031. Min Act: -0.0000

Data Index: 415601 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1049043 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1538. Min Act: -0.0000

Data Index: 51514 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1222393 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1441. Min Act: -0.0000

Data Index: 416873 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2427. Min Act: -0.0000

Data Index: 675404 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1355. Min Act: -0.0000

Data Index: 138619 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1079. Min Act: -0.0000

Data Index: 762629 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1085. Min Act: -0.0000

Data Index: 467293 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2187. Min Act: -0.0000

Data Index: 161303 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1059488 (C4 (Web Text))

Max Activating Token Index: 330