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

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

Neuron 205 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: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0001

Data Index: 894175 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4833. Min Act: -0.0001

Data Index: 781389 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4732. Min Act: -0.0001

Data Index: 55230 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1247483 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1111743 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4690. Min Act: -0.0001

Data Index: 69102 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4371. Min Act: -0.0000

Data Index: 220060 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4354. Min Act: -0.0001

Data Index: 195182 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4366. Min Act: -0.0000

Data Index: 360587 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4335. Min Act: -0.0001

Data Index: 111687 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1029559 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4138. Min Act: -0.0001

Data Index: 919492 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4241. Min Act: -0.0001

Data Index: 61814 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4113. Min Act: -0.0000

Data Index: 121583 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4393. Min Act: -0.0000

Data Index: 151973 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4215. Min Act: -0.0001

Data Index: 34737 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4189. Min Act: -0.0000

Data Index: 52035 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1310826 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1148474 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4186. Min Act: -0.0001

Data Index: 402624 (C4 (Web Text))

Max Activating Token Index: 296