Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 699 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.2205. Min Act: -0.0001

Data Index: 334417 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.2179. Min Act: -0.0001

Data Index: 689548 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0668. Min Act: -0.0001

Data Index: 1079351 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0320. Min Act: -0.0001

Data Index: 909049 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0479. Min Act: -0.0001

Data Index: 367818 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0618. Min Act: -0.0001

Data Index: 25429 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0108. Min Act: -0.0001

Data Index: 657695 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9279. Min Act: -0.0001

Data Index: 90469 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1055699 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1518924 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9710. Min Act: -0.0001

Data Index: 555383 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9431. Min Act: -0.0001

Data Index: 488036 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9088. Min Act: -0.0001

Data Index: 333573 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9591. Min Act: -0.0001

Data Index: 287423 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9323. Min Act: -0.0001

Data Index: 489879 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9506. Min Act: -0.0001

Data Index: 1649197 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9210. Min Act: -0.0001

Data Index: 838683 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9176. Min Act: -0.0001

Data Index: 207623 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9340. Min Act: -0.0001

Data Index: 95371 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9077. Min Act: -0.0001

Data Index: 811199 (C4 (Web Text))

Max Activating Token Index: 563