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

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

Neuron 1631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.6272. Min Act: -0.0000

Data Index: 605140 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5925. Min Act: -0.0001

Data Index: 1156417 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5965. Min Act: -0.0001

Data Index: 1198413 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1248533 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5624. Min Act: -0.0000

Data Index: 837740 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4865. Min Act: -0.0001

Data Index: 228706 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4777. Min Act: -0.0000

Data Index: 379571 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4589. Min Act: -0.0000

Data Index: 388312 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1078536 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4605. Min Act: -0.0001

Data Index: 34495 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1339189 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4374. Min Act: 0.0000

Data Index: 619883 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4179. Min Act: -0.0000

Data Index: 959980 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4139. Min Act: -0.0000

Data Index: 361136 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4243. Min Act: -0.0000

Data Index: 35055 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4272. Min Act: -0.0001

Data Index: 39643 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4210. Min Act: -0.0000

Data Index: 260454 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1000304 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4132. Min Act: -0.0000

Data Index: 102775 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4217. Min Act: -0.0001

Data Index: 245814 (C4 (Web Text))

Max Activating Token Index: 26