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

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

Neuron 1807 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0136. Min Range: -1.0136

Max Act: 1.0136. Min Act: -0.0000

Data Index: 640097 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1109233 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7712. Min Act: -0.0001

Data Index: 455259 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6149. Min Act: -0.0001

Data Index: 636363 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6257. Min Act: -0.0001

Data Index: 653913 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1210115 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1108253 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5721. Min Act: -0.0001

Data Index: 456691 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5890. Min Act: -0.0000

Data Index: 518729 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5870. Min Act: -0.0001

Data Index: 683099 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6202. Min Act: -0.0001

Data Index: 1210084 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5650. Min Act: -0.0001

Data Index: 794260 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5993. Min Act: -0.0000

Data Index: 396935 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1037082 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5831. Min Act: -0.0001

Data Index: 886062 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5838. Min Act: -0.0001

Data Index: 163154 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5626. Min Act: -0.0000

Data Index: 118024 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1319339 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5236. Min Act: -0.0000

Data Index: 10838 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5733. Min Act: -0.0000

Data Index: 470840 (C4 (Web Text))

Max Activating Token Index: 132