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

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

Neuron 4462 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.3176. Min Act: -0.0001

Data Index: 859123 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2946. Min Act: -0.0000

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2456. Min Act: -0.0000

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2808. Min Act: -0.0000

Data Index: 118244 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2592. Min Act: -0.0000

Data Index: 250423 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2686. Min Act: -0.0001

Data Index: 53972 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1302511 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.1994. Min Act: -0.0000

Data Index: 128163 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.1773. Min Act: -0.0000

Data Index: 723094 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2363. Min Act: -0.0000

Data Index: 674878 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1162672 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2006. Min Act: -0.0001

Data Index: 491207 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2160. Min Act: -0.0000

Data Index: 342164 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1221986 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2384. Min Act: -0.0001

Data Index: 731144 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1150194 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1078244 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2140. Min Act: -0.0000

Data Index: 257424 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2249. Min Act: -0.0000

Data Index: 818130 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.3176. Min Range: -0.3176

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1350920 (C4 (Web Text))

Max Activating Token Index: 640