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

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

Neuron 3302 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.4127. Min Act: -0.0001

Data Index: 747575 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.4049. Min Act: -0.0001

Data Index: 220504 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3796. Min Act: -0.0001

Data Index: 696995 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3887. Min Act: -0.0001

Data Index: 648819 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3522. Min Act: -0.0000

Data Index: 39405 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3708. Min Act: -0.0001

Data Index: 236784 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1228223 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3596. Min Act: -0.0001

Data Index: 99502 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3682. Min Act: -0.0001

Data Index: 283451 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3308. Min Act: -0.0001

Data Index: 552547 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3235. Min Act: -0.0001

Data Index: 743867 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3200. Min Act: -0.0000

Data Index: 656898 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1103031 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3207. Min Act: -0.0001

Data Index: 290439 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3282. Min Act: -0.0001

Data Index: 981149 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3486. Min Act: -0.0001

Data Index: 803046 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1043854 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3342. Min Act: -0.0001

Data Index: 679382 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1318220 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3256. Min Act: -0.0001

Data Index: 948567 (C4 (Web Text))

Max Activating Token Index: 470