Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2140 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2629. Min Act: -0.0002

Data Index: 413351 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2773. Min Act: -0.0002

Data Index: 63228 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2470. Min Act: -0.0002

Data Index: 223428 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2476. Min Act: -0.0002

Data Index: 512525 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2610. Min Act: -0.0002

Data Index: 687111 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2493. Min Act: -0.0002

Data Index: 972689 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2475. Min Act: -0.0002

Data Index: 1242588 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2301. Min Act: -0.0002

Data Index: 691519 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2107. Min Act: -0.0002

Data Index: 683669 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2341. Min Act: -0.0002

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2326. Min Act: -0.0002

Data Index: 745401 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2225. Min Act: -0.0002

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2230. Min Act: -0.0002

Data Index: 581146 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2191. Min Act: -0.0002

Data Index: 1267624 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2321. Min Act: -0.0002

Data Index: 832485 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2297. Min Act: -0.0002

Data Index: 184562 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2405. Min Act: -0.0002

Data Index: 861714 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2304. Min Act: -0.0002

Data Index: 602444 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2260. Min Act: -0.0002

Data Index: 62076 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.2773. Min Range: -0.2773

Max Act: 0.2453. Min Act: -0.0002

Data Index: 730222 (C4 (Web Text))

Max Activating Token Index: 739