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

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

Neuron 3216 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2987. Min Act: -0.0000

Data Index: 301208 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1088852 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2553. Min Act: -0.0000

Data Index: 95372 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2665. Min Act: -0.0001

Data Index: 833624 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2637. Min Act: -0.0000

Data Index: 606272 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1278581 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1086558 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2528. Min Act: -0.0000

Data Index: 966400 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1114817 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2508. Min Act: -0.0000

Data Index: 774771 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2585. Min Act: -0.0001

Data Index: 467203 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2292. Min Act: -0.0001

Data Index: 498098 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2208. Min Act: -0.0000

Data Index: 526955 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2367. Min Act: -0.0000

Data Index: 637935 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2348. Min Act: -0.0000

Data Index: 923983 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2189. Min Act: -0.0000

Data Index: 450299 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2255. Min Act: -0.0001

Data Index: 129877 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1319897 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2240. Min Act: -0.0000

Data Index: 995421 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2363. Min Act: -0.0001

Data Index: 187899 (C4 (Web Text))

Max Activating Token Index: 678