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

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

Neuron 2228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3481. Min Act: -0.0001

Data Index: 925613 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3264. Min Act: -0.0001

Data Index: 952583 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1654482 (Python Code)

Max Activating Token Index: 605

Text #3

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1010609 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2901. Min Act: -0.0001

Data Index: 342636 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3082. Min Act: -0.0001

Data Index: 347880 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1109194 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1457179 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2990. Min Act: -0.0001

Data Index: 658509 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1182374 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2718. Min Act: -0.0001

Data Index: 219600 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2809. Min Act: -0.0001

Data Index: 1525944 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2812. Min Act: -0.0001

Data Index: 968131 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1624286 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2653. Min Act: -0.0001

Data Index: 759207 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2632. Min Act: -0.0001

Data Index: 195959 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2479. Min Act: -0.0001

Data Index: 7313 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2505. Min Act: -0.0001

Data Index: 197837 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2450. Min Act: -0.0001

Data Index: 823425 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.3481. Min Range: -0.3481

Max Act: 0.2500. Min Act: -0.0001

Data Index: 829819 (C4 (Web Text))

Max Activating Token Index: 48