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

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

Neuron 1270 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7567. Min Act: -0.0000

Data Index: 148254 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7609. Min Act: -0.0000

Data Index: 970023 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1295817 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7123. Min Act: -0.0000

Data Index: 478897 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1074671 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7044. Min Act: -0.0000

Data Index: 250153 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5669. Min Act: -0.0000

Data Index: 462089 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6642. Min Act: -0.0000

Data Index: 688460 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6811. Min Act: -0.0000

Data Index: 662197 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1003465 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1007279 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1172308 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1140129 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6321. Min Act: -0.0000

Data Index: 737657 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5896. Min Act: -0.0000

Data Index: 26402 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6096. Min Act: -0.0000

Data Index: 900350 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6054. Min Act: -0.0000

Data Index: 45676 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5984. Min Act: -0.0000

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6151. Min Act: -0.0000

Data Index: 106708 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1296031 (C4 (Web Text))

Max Activating Token Index: 424