Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1130199 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4151. Min Act: -0.0001

Data Index: 1605934 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1048132 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3970. Min Act: -0.0000

Data Index: 754303 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1380562 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3389. Min Act: -0.0001

Data Index: 396999 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1386925 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2886. Min Act: -0.0000

Data Index: 197244 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3045. Min Act: -0.0000

Data Index: 858040 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2981. Min Act: -0.0000

Data Index: 149951 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2974. Min Act: -0.0000

Data Index: 566730 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2544. Min Act: -0.0000

Data Index: 811944 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2717. Min Act: -0.0000

Data Index: 805128 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1476243 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2712. Min Act: -0.0000

Data Index: 756541 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1450663 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1634173 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2715. Min Act: -0.0000

Data Index: 781665 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2611. Min Act: -0.0000

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.2671. Min Act: -0.0000

Data Index: 120744 (C4 (Web Text))

Max Activating Token Index: 189