Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 847 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1470751 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1529186 (Python Code)

Max Activating Token Index: 471

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1549214 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1481878 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1569782 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0310. Min Act: -0.0003

Data Index: 440851 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1378068 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1407056 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1382404 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0279. Min Act: -0.0003

Data Index: 731753 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1384560 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1387009 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0274. Min Act: -0.0003

Data Index: 340535 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1591733 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0275. Min Act: -0.0003

Data Index: 273149 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1580293 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1656396 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0264. Min Act: -0.0003

Data Index: 775038 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1415088 (Python Code)

Max Activating Token Index: 118

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1445761 (Python Code)

Max Activating Token Index: 403