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

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

Neuron 5558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1297. Min Range: -3.1297

Max Act: 3.1297. Min Act: -0.0001

Data Index: 1337334 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.6845. Min Act: -0.0001

Data Index: 253724 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.8304. Min Act: -0.0001

Data Index: 909960 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.6519. Min Act: -0.0000

Data Index: 1090764 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.6214. Min Act: -0.0001

Data Index: 1053187 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.5189. Min Act: -0.0000

Data Index: 635595 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2394. Min Act: -0.0000

Data Index: 647903 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.4486. Min Act: -0.0000

Data Index: 838220 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.3438. Min Act: -0.0000

Data Index: 529436 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2923. Min Act: -0.0001

Data Index: 1170971 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2753. Min Act: -0.0001

Data Index: 335458 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.1496. Min Act: -0.0000

Data Index: 742747 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2426. Min Act: -0.0001

Data Index: 721311 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1146844 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.3622. Min Act: -0.0000

Data Index: 124777 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.1301. Min Act: -0.0001

Data Index: 831323 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2318. Min Act: -0.0001

Data Index: 3968 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.2468. Min Act: -0.0000

Data Index: 325145 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.1300. Min Act: -0.0001

Data Index: 975838 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 3.1297. Min Range: -3.1297

Max Act: 2.1081. Min Act: -0.0000

Data Index: 453222 (C4 (Web Text))

Max Activating Token Index: 257