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

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

Neuron 3448 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7664. Min Act: -0.0000

Data Index: 1154206 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1130496 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7301. Min Act: -0.0000

Data Index: 1175863 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 2.0259. Min Range: -2.0259

Max Act: 2.0259. Min Act: -0.0000

Data Index: 731752 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5306. Min Act: -0.0000

Data Index: 92981 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6489. Min Act: -0.0000

Data Index: 76410 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5892. Min Act: -0.0000

Data Index: 812299 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1252866 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5165. Min Act: -0.0000

Data Index: 74052 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5089. Min Act: -0.0000

Data Index: 972248 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.4651. Min Act: -0.0000

Data Index: 106617 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5023. Min Act: -0.0000

Data Index: 455542 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6113. Min Act: -0.0000

Data Index: 964030 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1326729 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.5445. Min Act: -0.0000

Data Index: 211362 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.3977. Min Act: -0.0000

Data Index: 79311 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.4364. Min Act: -0.0000

Data Index: 92139 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.3915. Min Act: -0.0000

Data Index: 962091 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1346202 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1243079 (C4 (Web Text))

Max Activating Token Index: 803