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

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

Neuron 3072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3746. Min Act: -0.0000

Data Index: 454612 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3182. Min Act: -0.0001

Data Index: 948640 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3530. Min Act: -0.0001

Data Index: 281714 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3206. Min Act: -0.0001

Data Index: 398702 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3235. Min Act: -0.0001

Data Index: 356532 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3319. Min Act: -0.0000

Data Index: 433814 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3238. Min Act: -0.0001

Data Index: 46403 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3144. Min Act: -0.0001

Data Index: 611790 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1286988 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3341. Min Act: -0.0000

Data Index: 14701 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3228. Min Act: -0.0001

Data Index: 1320776 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3230. Min Act: -0.0001

Data Index: 162310 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3395. Min Act: -0.0001

Data Index: 919220 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3338. Min Act: -0.0000

Data Index: 689557 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1219735 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1054544 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1165697 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3161. Min Act: -0.0001

Data Index: 840037 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3204. Min Act: -0.0001

Data Index: 285296 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.3746. Min Range: -0.3746

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1342898 (C4 (Web Text))

Max Activating Token Index: 690