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

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

Neuron 2008 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: 4.0224. Min Range: -4.0224

Max Act: 4.0224. Min Act: -0.0000

Data Index: 828417 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.8843. Min Act: -0.0000

Data Index: 715296 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 4.0224. Min Range: -4.0224

Max Act: 4.0213. Min Act: -0.0000

Data Index: 1261602 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.7315. Min Act: -0.0000

Data Index: 920020 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.8369. Min Act: -0.0000

Data Index: 783343 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.7814. Min Act: -0.0000

Data Index: 406645 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.7377. Min Act: -0.0000

Data Index: 41525 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.4857. Min Act: -0.0000

Data Index: 873259 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5163. Min Act: -0.0000

Data Index: 449036 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.6042. Min Act: -0.0000

Data Index: 391071 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5961. Min Act: -0.0000

Data Index: 434762 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5665. Min Act: -0.0000

Data Index: 844476 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5567. Min Act: -0.0000

Data Index: 443576 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.3684. Min Act: -0.0000

Data Index: 1340242 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5026. Min Act: -0.0000

Data Index: 599229 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.8026. Min Act: -0.0000

Data Index: 1052400 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5855. Min Act: -0.0000

Data Index: 99113 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.5177. Min Act: -0.0000

Data Index: 179859 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.3048. Min Act: -0.0000

Data Index: 1167094 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 4.0224. Min Range: -4.0224

Max Act: 3.1653. Min Act: -0.0000

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 455