Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1836 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0006

Data Index: 903147 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1221196 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0266. Min Act: -0.0006

Data Index: 110084 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0282. Min Act: -0.0006

Data Index: 936322 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0261. Min Act: -0.0006

Data Index: 964991 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0260. Min Act: -0.0006

Data Index: 273268 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0258. Min Act: -0.0006

Data Index: 852835 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0270. Min Act: -0.0006

Data Index: 950882 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0258. Min Act: -0.0006

Data Index: 803211 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0255. Min Act: -0.0006

Data Index: 267367 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0258. Min Act: -0.0006

Data Index: 487994 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0249. Min Act: -0.0006

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1347239 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0253. Min Act: -0.0006

Data Index: 66700 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0252. Min Act: -0.0006

Data Index: 3141 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0252. Min Act: -0.0006

Data Index: 195367 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0246. Min Act: -0.0006

Data Index: 283755 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0254. Min Act: -0.0006

Data Index: 246154 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0253. Min Act: -0.0006

Data Index: 559096 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1070625 (C4 (Web Text))

Max Activating Token Index: 1022