Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1763. Min Act: -0.0002

Data Index: 807229 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1636. Min Act: -0.0002

Data Index: 587078 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1647. Min Act: -0.0002

Data Index: 357277 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1075793 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1428. Min Act: -0.0002

Data Index: 676798 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1436. Min Act: -0.0002

Data Index: 324217 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1350. Min Act: -0.0002

Data Index: 594199 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1465. Min Act: -0.0002

Data Index: 214897 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1454. Min Act: -0.0002

Data Index: 1294074 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1269441 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1514. Min Act: -0.0002

Data Index: 529425 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1456. Min Act: -0.0002

Data Index: 319270 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1528. Min Act: -0.0002

Data Index: 982250 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1428. Min Act: -0.0002

Data Index: 203197 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1108772 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1342. Min Act: -0.0002

Data Index: 1341975 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1116126 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1448. Min Act: -0.0002

Data Index: 270360 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1150679 (C4 (Web Text))

Max Activating Token Index: 956