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

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

Neuron 2645 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4059. Min Act: -0.0000

Data Index: 35201 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1188557 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4025. Min Act: 0.0000

Data Index: 1222362 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4025. Min Act: -0.0000

Data Index: 136089 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3325. Min Act: -0.0000

Data Index: 698925 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3425. Min Act: -0.0000

Data Index: 598399 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1295042 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1239143 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3116. Min Act: -0.0000

Data Index: 803385 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3221. Min Act: -0.0000

Data Index: 507901 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3087. Min Act: -0.0000

Data Index: 323950 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3074. Min Act: -0.0000

Data Index: 968275 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1011593 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3071. Min Act: -0.0000

Data Index: 718239 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1074395 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3008. Min Act: -0.0000

Data Index: 727876 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3095. Min Act: -0.0000

Data Index: 451569 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3196. Min Act: -0.0000

Data Index: 754828 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1227215 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.2799. Min Act: -0.0000

Data Index: 508242 (C4 (Web Text))

Max Activating Token Index: 732