Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1225. Min Act: -0.0001

Data Index: 398850 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1259. Min Act: 0.0001

Data Index: 686908 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1063. Min Act: 0.0002

Data Index: 944452 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1000. Min Act: 0.0001

Data Index: 895861 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0990. Min Act: -0.0000

Data Index: 410438 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1039522 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0966. Min Act: -0.0001

Data Index: 247492 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0961. Min Act: -0.0000

Data Index: 419027 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1319902 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0900. Min Act: -0.0001

Data Index: 291518 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0973. Min Act: -0.0001

Data Index: 15166 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0898. Min Act: -0.0000

Data Index: 687801 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0939. Min Act: -0.0001

Data Index: 562952 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0919. Min Act: -0.0001

Data Index: 641632 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1110802 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0902. Min Act: -0.0000

Data Index: 633446 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0900. Min Act: -0.0001

Data Index: 260135 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0888. Min Act: -0.0001

Data Index: 354398 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0880. Min Act: -0.0001

Data Index: 866034 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0872. Min Act: -0.0001

Data Index: 723522 (C4 (Web Text))

Max Activating Token Index: 700