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

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

Neuron 3803 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: 0.4350. Min Range: -0.4350

Max Act: 0.4350. Min Act: -0.0000

Data Index: 969125 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1264882 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3694. Min Act: -0.0000

Data Index: 678867 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3668. Min Act: -0.0000

Data Index: 574211 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3640. Min Act: -0.0000

Data Index: 80724 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1208942 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3510. Min Act: -0.0000

Data Index: 171797 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3533. Min Act: -0.0000

Data Index: 917906 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3633. Min Act: -0.0000

Data Index: 481956 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3502. Min Act: -0.0000

Data Index: 147136 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3311. Min Act: -0.0000

Data Index: 746260 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3295. Min Act: -0.0000

Data Index: 372826 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3380. Min Act: -0.0000

Data Index: 807691 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3349. Min Act: -0.0000

Data Index: 149871 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1288743 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3320. Min Act: -0.0000

Data Index: 720003 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1322535 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1141416 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1083887 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3206. Min Act: -0.0000

Data Index: 76051 (C4 (Web Text))

Max Activating Token Index: 844