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

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

Neuron 339 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: 1.0979. Min Range: -1.0979

Max Act: 1.0979. Min Act: -0.0001

Data Index: 165332 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8741. Min Act: -0.0001

Data Index: 936362 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8609. Min Act: -0.0001

Data Index: 116989 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8717. Min Act: -0.0001

Data Index: 554331 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8838. Min Act: -0.0001

Data Index: 806019 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8586. Min Act: -0.0001

Data Index: 1082777 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8330. Min Act: -0.0001

Data Index: 428763 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8236. Min Act: -0.0001

Data Index: 331042 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8258. Min Act: -0.0001

Data Index: 528100 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8416. Min Act: -0.0001

Data Index: 1295286 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7524. Min Act: -0.0001

Data Index: 323110 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7539. Min Act: -0.0001

Data Index: 1061319 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1307810 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7316. Min Act: -0.0001

Data Index: 399086 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7824. Min Act: -0.0001

Data Index: 959123 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.8210. Min Act: -0.0001

Data Index: 84158 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7440. Min Act: -0.0001

Data Index: 584191 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7296. Min Act: -0.0001

Data Index: 546501 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.6445. Min Act: -0.0001

Data Index: 271638 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.0979. Min Range: -1.0979

Max Act: 0.7480. Min Act: -0.0001

Data Index: 194559 (C4 (Web Text))

Max Activating Token Index: 679