Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2199 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1014916 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5780. Min Act: -0.0000

Data Index: 46216 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5290. Min Act: -0.0000

Data Index: 221157 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5681. Min Act: -0.0000

Data Index: 838007 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5197. Min Act: -0.0000

Data Index: 974303 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5495. Min Act: -0.0000

Data Index: 452889 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5050. Min Act: -0.0000

Data Index: 643470 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4578. Min Act: -0.0000

Data Index: 247923 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4393. Min Act: -0.0000

Data Index: 800151 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4423. Min Act: -0.0000

Data Index: 240263 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4349. Min Act: -0.0000

Data Index: 496888 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4413. Min Act: -0.0000

Data Index: 126050 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4415. Min Act: -0.0000

Data Index: 683470 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4354. Min Act: -0.0000

Data Index: 537175 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4230. Min Act: -0.0000

Data Index: 350979 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4232. Min Act: -0.0000

Data Index: 611354 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4298. Min Act: -0.0000

Data Index: 258601 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4135. Min Act: -0.0000

Data Index: 93450 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4200. Min Act: -0.0000

Data Index: 971858 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4196. Min Act: -0.0000

Data Index: 27862 (C4 (Web Text))

Max Activating Token Index: 452