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

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

Neuron 250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1040545 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.7553. Min Act: -0.0000

Data Index: 354207 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.6867. Min Act: -0.0000

Data Index: 734031 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.7136. Min Act: -0.0000

Data Index: 887989 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.3022. Min Act: -0.0000

Data Index: 1027997 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.5154. Min Act: -0.0000

Data Index: 781789 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.3540. Min Act: -0.0000

Data Index: 445595 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.3399. Min Act: -0.0000

Data Index: 588288 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.2081. Min Act: -0.0000

Data Index: 247524 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.3182. Min Act: -0.0000

Data Index: 290208 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.3017. Min Act: -0.0000

Data Index: 439393 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.2744. Min Act: -0.0000

Data Index: 320039 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.2703. Min Act: -0.0000

Data Index: 733740 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.1499. Min Act: -0.0000

Data Index: 394058 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1196159 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.1660. Min Act: -0.0000

Data Index: 1059969 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1008727 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.0169. Min Act: -0.0000

Data Index: 1047417 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.0217. Min Act: -0.0000

Data Index: 358795 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 2.9234. Min Range: -2.9234

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1016170 (C4 (Web Text))

Max Activating Token Index: 289