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

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

Neuron 3070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0001

Data Index: 428862 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1174717 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3749. Min Act: -0.0001

Data Index: 1280446 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1052265 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1261360 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3687. Min Act: -0.0001

Data Index: 530679 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3638. Min Act: -0.0001

Data Index: 581077 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3039. Min Act: -0.0001

Data Index: 401154 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3247. Min Act: -0.0001

Data Index: 33160 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3340. Min Act: -0.0001

Data Index: 560030 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3126. Min Act: -0.0001

Data Index: 907813 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3301. Min Act: -0.0000

Data Index: 241386 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3173. Min Act: -0.0001

Data Index: 545624 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3115. Min Act: -0.0001

Data Index: 881824 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3315. Min Act: -0.0001

Data Index: 965574 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3202. Min Act: -0.0001

Data Index: 184227 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3274. Min Act: -0.0001

Data Index: 550823 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3053. Min Act: -0.0001

Data Index: 372834 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3070. Min Act: -0.0001

Data Index: 376123 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3128. Min Act: -0.0001

Data Index: 234400 (C4 (Web Text))

Max Activating Token Index: 653