Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1344 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3540. Min Act: -0.0001

Data Index: 8429 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3560. Min Act: -0.0001

Data Index: 1269121 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3550. Min Act: -0.0001

Data Index: 953017 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3298. Min Act: -0.0001

Data Index: 128634 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3163. Min Act: -0.0001

Data Index: 190425 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1153716 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3238. Min Act: -0.0001

Data Index: 238561 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3166. Min Act: -0.0001

Data Index: 526983 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3304. Min Act: -0.0001

Data Index: 178154 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2830. Min Act: -0.0001

Data Index: 1119683 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3254. Min Act: -0.0001

Data Index: 604735 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3240. Min Act: -0.0001

Data Index: 460714 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2982. Min Act: -0.0001

Data Index: 80991 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3069. Min Act: -0.0001

Data Index: 577746 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3148. Min Act: -0.0001

Data Index: 158854 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1215343 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1244712 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3404. Min Act: -0.0001

Data Index: 151799 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1338177 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3035. Min Act: -0.0001

Data Index: 987045 (C4 (Web Text))

Max Activating Token Index: 814