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

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

Neuron 1608 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: 0.4250. Min Range: -0.4250

Max Act: 0.4221. Min Act: -0.0000

Data Index: 963845 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0000

Data Index: 153895 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3629. Min Act: -0.0000

Data Index: 351329 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3438. Min Act: -0.0000

Data Index: 390693 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3945. Min Act: -0.0001

Data Index: 864570 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3619. Min Act: -0.0001

Data Index: 98155 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1033069 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3570. Min Act: -0.0001

Data Index: 594999 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3356. Min Act: -0.0000

Data Index: 312830 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3582. Min Act: -0.0000

Data Index: 607868 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1247357 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3942. Min Act: -0.0000

Data Index: 626122 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3527. Min Act: -0.0000

Data Index: 592308 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1180812 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3402. Min Act: -0.0000

Data Index: 17643 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1040815 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3250. Min Act: -0.0001

Data Index: 486824 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1239586 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3301. Min Act: -0.0000

Data Index: 318218 (C4 (Web Text))

Max Activating Token Index: 16