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

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

Neuron 640 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: 0.0317. Min Range: -0.0317

Max Act: 0.0312. Min Act: -0.0006

Data Index: 747862 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0314. Min Act: -0.0006

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1124066 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0316. Min Act: -0.0006

Data Index: 127582 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0299. Min Act: -0.0006

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0310. Min Act: -0.0006

Data Index: 712801 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0305. Min Act: -0.0006

Data Index: 511201 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1049100 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0291. Min Act: -0.0006

Data Index: 301282 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0006

Data Index: 124956 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0289. Min Act: -0.0006

Data Index: 918663 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0006

Data Index: 248727 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1352263 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0278. Min Act: -0.0006

Data Index: 353111 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0006

Data Index: 248335 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1298164 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0288. Min Act: -0.0006

Data Index: 540134 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0280. Min Act: -0.0006

Data Index: 542693 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0287. Min Act: -0.0006

Data Index: 456010 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0275. Min Act: -0.0006

Data Index: 916332 (C4 (Web Text))

Max Activating Token Index: 386