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

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

Neuron 2635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5175. Min Act: -0.0001

Data Index: 1284727 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 875520 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5177. Min Act: -0.0001

Data Index: 548477 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4854. Min Act: -0.0001

Data Index: 94772 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4837. Min Act: -0.0001

Data Index: 567779 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4411. Min Act: -0.0001

Data Index: 60531 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4335. Min Act: -0.0001

Data Index: 114113 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4277. Min Act: -0.0000

Data Index: 488525 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4243. Min Act: -0.0001

Data Index: 218588 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4175. Min Act: -0.0000

Data Index: 390620 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4008. Min Act: -0.0001

Data Index: 522600 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4026. Min Act: -0.0000

Data Index: 634329 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3928. Min Act: -0.0001

Data Index: 893202 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3743. Min Act: -0.0001

Data Index: 690775 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3730. Min Act: -0.0000

Data Index: 557967 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3533. Min Act: -0.0001

Data Index: 744348 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3853. Min Act: -0.0001

Data Index: 55481 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3649. Min Act: -0.0001

Data Index: 835056 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1170705 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4082. Min Act: -0.0001

Data Index: 218359 (C4 (Web Text))

Max Activating Token Index: 228