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

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

Neuron 550 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: 1.4552. Min Range: -1.4552

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1081577 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.3761. Min Act: -0.0000

Data Index: 522788 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.3538. Min Act: -0.0000

Data Index: 755777 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.3320. Min Act: -0.0000

Data Index: 688543 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1262693 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2364. Min Act: -0.0000

Data Index: 764012 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2215. Min Act: -0.0000

Data Index: 970413 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2577. Min Act: -0.0000

Data Index: 236502 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1256843 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2235. Min Act: -0.0000

Data Index: 628378 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.2156. Min Act: -0.0000

Data Index: 251195 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1262. Min Act: -0.0000

Data Index: 11943 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1835. Min Act: -0.0000

Data Index: 376391 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1782. Min Act: -0.0000

Data Index: 40455 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1122. Min Act: -0.0000

Data Index: 542572 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.0904. Min Act: -0.0000

Data Index: 672927 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1197. Min Act: -0.0000

Data Index: 375767 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.0316. Min Act: -0.0000

Data Index: 297528 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1328826 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.4552. Min Range: -1.4552

Max Act: 1.0988. Min Act: -0.0000

Data Index: 295296 (C4 (Web Text))

Max Activating Token Index: 426