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

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

Neuron 2966 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.4149. Min Act: -0.0000

Data Index: 446823 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1261910 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3944. Min Act: -0.0000

Data Index: 391933 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3787. Min Act: -0.0000

Data Index: 56278 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1260654 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1077651 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1260635 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3355. Min Act: -0.0000

Data Index: 661996 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1039372 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1335371 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3587. Min Act: -0.0000

Data Index: 223957 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1050969 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1193955 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1016620 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3143. Min Act: -0.0000

Data Index: 312927 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3247. Min Act: -0.0000

Data Index: 599105 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3241. Min Act: -0.0000

Data Index: 944044 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1331507 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3244. Min Act: -0.0000

Data Index: 555950 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.4149. Min Range: -0.4149

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1177067 (C4 (Web Text))

Max Activating Token Index: 94