Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 661 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1067269 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0003

Data Index: 61321 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0378. Min Act: -0.0003

Data Index: 647612 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1639931 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1649909 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1654865 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1208324 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0341. Min Act: -0.0003

Data Index: 612915 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0327. Min Act: -0.0003

Data Index: 6457 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1626179 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0334. Min Act: -0.0003

Data Index: 454620 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1391609 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1564270 (Python Code)

Max Activating Token Index: 645

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0327. Min Act: -0.0003

Data Index: 549549 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1459816 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1559779 (Python Code)

Max Activating Token Index: 645

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1486089 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1416199 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1478502 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0321. Min Act: -0.0003

Data Index: 885066 (C4 (Web Text))

Max Activating Token Index: 111