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

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

Neuron 42 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: 0.4950. Min Range: -0.4950

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1269040 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4796. Min Act: -0.0000

Data Index: 940324 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4471. Min Act: -0.0000

Data Index: 561437 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4627. Min Act: -0.0001

Data Index: 681441 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4715. Min Act: -0.0000

Data Index: 777026 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4502. Min Act: -0.0000

Data Index: 668132 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4404. Min Act: -0.0001

Data Index: 617027 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4291. Min Act: -0.0001

Data Index: 1113518 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4347. Min Act: -0.0000

Data Index: 936561 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1342037 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1131975 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4368. Min Act: -0.0001

Data Index: 637518 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4243. Min Act: -0.0000

Data Index: 734217 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4257. Min Act: -0.0000

Data Index: 178560 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3977. Min Act: -0.0000

Data Index: 520307 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1179106 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1079445 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1073060 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3818. Min Act: -0.0000

Data Index: 653812 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4072. Min Act: -0.0000

Data Index: 577570 (C4 (Web Text))

Max Activating Token Index: 252