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

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

Neuron 535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0004

Data Index: 7002 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0339. Min Act: -0.0004

Data Index: 931882 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1692 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0330. Min Act: -0.0004

Data Index: 611330 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0325. Min Act: -0.0004

Data Index: 399225 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0324. Min Act: -0.0004

Data Index: 431542 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0317. Min Act: -0.0004

Data Index: 782324 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0322. Min Act: -0.0005

Data Index: 79320 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0315. Min Act: -0.0004

Data Index: 137000 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0314. Min Act: -0.0004

Data Index: 263319 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0320. Min Act: -0.0004

Data Index: 422972 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1256910 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0314. Min Act: -0.0004

Data Index: 644428 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1476995 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1191648 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0312. Min Act: -0.0005

Data Index: 789178 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0311. Min Act: -0.0004

Data Index: 1240301 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0305. Min Act: -0.0005

Data Index: 847530 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1126243 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1587270 (Python Code)

Max Activating Token Index: 635