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

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

Neuron 979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0001

Data Index: 483842 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1315592 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0305. Min Act: -0.0001

Data Index: 62056 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1496592 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0001

Data Index: 905544 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0288. Min Act: -0.0001

Data Index: 463917 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0269. Min Act: -0.0001

Data Index: 59170 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1435037 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1421178 (Python Code)

Max Activating Token Index: 637

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1490230 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0276. Min Act: -0.0001

Data Index: 119635 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1598972 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1215948 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1435309 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1293320 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0239. Min Act: -0.0001

Data Index: 968256 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0251. Min Act: -0.0001

Data Index: 24692 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1279597 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0241. Min Act: -0.0001

Data Index: 8678 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0242. Min Act: -0.0001

Data Index: 633029 (C4 (Web Text))

Max Activating Token Index: 765