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

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

Neuron 4552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0402. Min Range: -5.0402

Max Act: 5.0402. Min Act: -0.0000

Data Index: 29836 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.8535. Min Act: -0.0000

Data Index: 1216024 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 5.0402. Min Range: -5.0402

Max Act: 5.0162. Min Act: -0.0000

Data Index: 214553 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.6006. Min Act: -0.0000

Data Index: 1074780 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.5883. Min Act: -0.0000

Data Index: 65457 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.2022. Min Act: -0.0000

Data Index: 244330 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.2016. Min Act: -0.0000

Data Index: 1133978 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.4765. Min Act: -0.0000

Data Index: 1241065 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.2812. Min Act: -0.0000

Data Index: 128484 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.0314. Min Act: -0.0000

Data Index: 252717 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.2076. Min Act: -0.0000

Data Index: 1253099 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.0139. Min Act: -0.0000

Data Index: 11670 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1924. Min Act: -0.0000

Data Index: 772203 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1698. Min Act: -0.0000

Data Index: 815017 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1010. Min Act: -0.0000

Data Index: 1087205 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.9585. Min Act: -0.0000

Data Index: 284556 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.9371. Min Act: -0.0000

Data Index: 243227 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1801. Min Act: -0.0000

Data Index: 351048 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.0137. Min Act: -0.0000

Data Index: 2816 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1964. Min Act: -0.0000

Data Index: 1072797 (C4 (Web Text))

Max Activating Token Index: 696