Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5079 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.6230. Min Act: -0.0000

Data Index: 16120 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1334782 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.6683. Min Act: -0.0000

Data Index: 875971 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4146. Min Act: -0.0000

Data Index: 786251 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1204037 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1258767 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1479. Min Act: -0.0000

Data Index: 912197 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0910. Min Act: -0.0000

Data Index: 949875 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0216. Min Act: -0.0000

Data Index: 342432 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1149. Min Act: -0.0000

Data Index: 17360 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.1357. Min Act: -0.0000

Data Index: 563139 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0680. Min Act: -0.0000

Data Index: 742913 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1040401 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1127304 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0225. Min Act: -0.0000

Data Index: 657354 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0188. Min Act: -0.0000

Data Index: 1043976 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.6683. Min Range: -1.6683

Max Act: 0.9945. Min Act: -0.0000

Data Index: 94670 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.6683. Min Range: -1.6683

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1203664 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.6683. Min Range: -1.6683

Max Act: 0.9599. Min Act: -0.0000

Data Index: 428437 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.6683. Min Range: -1.6683

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1080867 (C4 (Web Text))

Max Activating Token Index: 61