Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 26 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1632817 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1407497 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1501533 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1552209 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1022678 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0296. Min Act: -0.0002

Data Index: 257385 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0300. Min Act: -0.0003

Data Index: 333114 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0301. Min Act: -0.0002

Data Index: 267261 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0295. Min Act: -0.0002

Data Index: 61725 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0288. Min Act: -0.0002

Data Index: 233887 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1369868 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0269. Min Act: -0.0002

Data Index: 249543 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1445825 (Python Code)

Max Activating Token Index: 913

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1007630 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1448134 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1609434 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0257. Min Act: -0.0002

Data Index: 794946 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0260. Min Act: -0.0002

Data Index: 592542 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0254. Min Act: -0.0002

Data Index: 71934 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1133234 (C4 (Web Text))

Max Activating Token Index: 747