Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0006

Data Index: 786375 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0360. Min Act: -0.0006

Data Index: 246615 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0319. Min Act: -0.0006

Data Index: 338740 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0301. Min Act: -0.0006

Data Index: 335054 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0323. Min Act: -0.0006

Data Index: 883362 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1266324 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0328. Min Act: -0.0006

Data Index: 512667 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0314. Min Act: -0.0006

Data Index: 311034 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0300. Min Act: -0.0006

Data Index: 957828 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0320. Min Act: -0.0006

Data Index: 136856 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0306. Min Act: -0.0006

Data Index: 78262 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1350463 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0304. Min Act: -0.0006

Data Index: 323423 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0302. Min Act: -0.0006

Data Index: 576481 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1034665 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0301. Min Act: -0.0006

Data Index: 4744 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0293. Min Act: -0.0006

Data Index: 943162 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1293693 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0268. Min Act: -0.0006

Data Index: 995897 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1112864 (C4 (Web Text))

Max Activating Token Index: 26