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

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

Neuron 2470 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0002

Data Index: 556765 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0487. Min Act: -0.0002

Data Index: 571172 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0458. Min Act: -0.0002

Data Index: 497874 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0455. Min Act: -0.0002

Data Index: 183678 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0444. Min Act: -0.0003

Data Index: 682054 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1276052 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0003

Data Index: 22816 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0426. Min Act: -0.0002

Data Index: 950506 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0424. Min Act: -0.0002

Data Index: 300966 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1317060 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1297679 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0389. Min Act: -0.0002

Data Index: 551763 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0391. Min Act: -0.0003

Data Index: 147106 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0373. Min Act: -0.0003

Data Index: 375473 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0373. Min Act: -0.0003

Data Index: 914599 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0372. Min Act: -0.0003

Data Index: 306693 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0369. Min Act: -0.0002

Data Index: 715332 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1123676 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0366. Min Act: -0.0002

Data Index: 758103 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0362. Min Act: -0.0002

Data Index: 22135 (C4 (Web Text))

Max Activating Token Index: 937