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

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

Neuron 2910 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: 1.8939. Min Range: -1.8939

Max Act: 1.8939. Min Act: -0.0001

Data Index: 606971 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.6212. Min Act: -0.0001

Data Index: 27592 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.6216. Min Act: -0.0001

Data Index: 406770 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.6522. Min Act: -0.0001

Data Index: 1058006 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.5676. Min Act: -0.0001

Data Index: 252843 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.5053. Min Act: -0.0001

Data Index: 1075387 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3534. Min Act: -0.0001

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.5577. Min Act: -0.0001

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.4946. Min Act: -0.0001

Data Index: 528917 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.4573. Min Act: -0.0001

Data Index: 1109245 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3528. Min Act: -0.0001

Data Index: 791843 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3675. Min Act: -0.0001

Data Index: 180235 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3890. Min Act: -0.0001

Data Index: 152103 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3519. Min Act: -0.0001

Data Index: 901388 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3155. Min Act: -0.0001

Data Index: 1156037 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3046. Min Act: -0.0001

Data Index: 507531 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.3000. Min Act: -0.0001

Data Index: 481361 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.1711. Min Act: -0.0001

Data Index: 607055 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.2807. Min Act: -0.0001

Data Index: 689236 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.8939. Min Range: -1.8939

Max Act: 1.2096. Min Act: -0.0001

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 500