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

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

Neuron 130 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.5288. Min Act: -0.0000

Data Index: 489367 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1027719 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1203299 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4177. Min Act: -0.0000

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1021551 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1287979 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4061. Min Act: 0.0000

Data Index: 1189931 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4219. Min Act: -0.0000

Data Index: 337769 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4059. Min Act: -0.0000

Data Index: 46078 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3710. Min Act: -0.0000

Data Index: 767807 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3585. Min Act: -0.0000

Data Index: 140074 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1193499 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3548. Min Act: -0.0000

Data Index: 396735 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3544. Min Act: -0.0000

Data Index: 680655 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3505. Min Act: -0.0000

Data Index: 213840 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3524. Min Act: -0.0000

Data Index: 333496 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3467. Min Act: 0.0000

Data Index: 1233216 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.2922. Min Act: -0.0000

Data Index: 268955 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3159. Min Act: -0.0000

Data Index: 584702 (C4 (Web Text))

Max Activating Token Index: 621