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

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

Neuron 1502 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: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0000

Data Index: 131000 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4910. Min Act: -0.0001

Data Index: 846814 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4888. Min Act: -0.0000

Data Index: 650205 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1313102 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4432. Min Act: -0.0000

Data Index: 125657 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4485. Min Act: -0.0000

Data Index: 21232 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4378. Min Act: -0.0001

Data Index: 986933 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4290. Min Act: -0.0001

Data Index: 378526 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4324. Min Act: -0.0001

Data Index: 52326 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4275. Min Act: -0.0001

Data Index: 368297 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4436. Min Act: -0.0000

Data Index: 567318 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4280. Min Act: -0.0001

Data Index: 701304 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4229. Min Act: -0.0001

Data Index: 657020 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4213. Min Act: -0.0001

Data Index: 765673 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4185. Min Act: -0.0001

Data Index: 599261 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4191. Min Act: -0.0000

Data Index: 799749 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1234288 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4169. Min Act: -0.0000

Data Index: 338715 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4158. Min Act: -0.0001

Data Index: 847551 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4001. Min Act: -0.0000

Data Index: 687821 (C4 (Web Text))

Max Activating Token Index: 137