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

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

Neuron 2675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.3359. Min Act: -0.0001

Data Index: 215868 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.3242. Min Act: -0.0000

Data Index: 344793 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.3019. Min Act: -0.0001

Data Index: 903944 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.3203. Min Act: -0.0000

Data Index: 682171 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2715. Min Act: -0.0001

Data Index: 481058 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2540. Min Act: -0.0000

Data Index: 843351 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2700. Min Act: -0.0000

Data Index: 824911 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2454. Min Act: -0.0001

Data Index: 803076 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2352. Min Act: -0.0001

Data Index: 959001 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2225. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1197048 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2029. Min Act: -0.0001

Data Index: 498363 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1198608 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1919. Min Act: -0.0001

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1888. Min Act: -0.0001

Data Index: 96572 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1970. Min Act: -0.0001

Data Index: 464469 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1829. Min Act: -0.0001

Data Index: 832992 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1744. Min Act: -0.0000

Data Index: 442072 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1724. Min Act: -0.0001

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.3359. Min Range: -0.3359

Max Act: 0.1577. Min Act: -0.0001

Data Index: 756814 (C4 (Web Text))

Max Activating Token Index: 985