Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 338890 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3354. Min Act: -0.0000

Data Index: 785186 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1183451 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2571. Min Act: -0.0000

Data Index: 433204 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2566. Min Act: -0.0000

Data Index: 550453 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2453. Min Act: -0.0000

Data Index: 523458 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2406. Min Act: -0.0000

Data Index: 572819 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2457. Min Act: -0.0000

Data Index: 764354 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1145226 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2342. Min Act: -0.0000

Data Index: 664935 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2253. Min Act: -0.0000

Data Index: 731310 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2345. Min Act: -0.0000

Data Index: 850176 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2307. Min Act: -0.0000

Data Index: 231302 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1006792 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1255531 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2311. Min Act: -0.0000

Data Index: 979866 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2232. Min Act: -0.0000

Data Index: 999307 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2414. Min Act: -0.0000

Data Index: 587942 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2281. Min Act: -0.0000

Data Index: 846732 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2178. Min Act: -0.0001

Data Index: 383521 (C4 (Web Text))

Max Activating Token Index: 186