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

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

Neuron 2017 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2844. Min Act: -0.0000

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1245779 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2509. Min Act: -0.0000

Data Index: 226654 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2468. Min Act: -0.0001

Data Index: 12570 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1163157 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2454. Min Act: -0.0001

Data Index: 493663 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2526. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2544. Min Act: -0.0001

Data Index: 114281 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2527. Min Act: -0.0001

Data Index: 80030 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2196. Min Act: -0.0000

Data Index: 486124 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1309900 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1116806 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2300. Min Act: -0.0000

Data Index: 459369 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2292. Min Act: -0.0000

Data Index: 677604 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1118502 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2186. Min Act: -0.0001

Data Index: 24195 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2090. Min Act: -0.0000

Data Index: 187330 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2207. Min Act: -0.0000

Data Index: 704248 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2100. Min Act: -0.0000

Data Index: 441499 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.2844. Min Range: -0.2844

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 807