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

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

Neuron 2136 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3539. Min Act: -0.0001

Data Index: 15177 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3638. Min Act: -0.0001

Data Index: 1586016 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.2802. Min Act: -0.0001

Data Index: 77759 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.4280. Min Act: -0.0001

Data Index: 234521 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3444. Min Act: -0.0001

Data Index: 1633259 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3273. Min Act: -0.0001

Data Index: 1560727 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3180. Min Act: -0.0001

Data Index: 1379657 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.2534. Min Act: -0.0001

Data Index: 1412535 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1277. Min Act: -0.0001

Data Index: 282861 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1986. Min Act: -0.0001

Data Index: 627160 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1844. Min Act: -0.0001

Data Index: 1555998 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.2440. Min Act: -0.0001

Data Index: 941556 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.0999. Min Act: -0.0001

Data Index: 1564565 (Python Code)

Max Activating Token Index: 174

Text #13

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.2685. Min Act: -0.0001

Data Index: 1588830 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1453018 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1725. Min Act: -0.0001

Data Index: 1588251 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1345. Min Act: -0.0001

Data Index: 1632841 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.3567. Min Act: -0.0001

Data Index: 1363167 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.2695. Min Act: -0.0001

Data Index: 583093 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.4280. Min Range: -1.4280

Max Act: 1.1859. Min Act: -0.0001

Data Index: 1395569 (Python Code)

Max Activating Token Index: 481