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

Dataset: The Pile

Neuron 2917 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6669. Min Act: -0.0000

Data Index: 1046909 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4411. Min Act: -0.0000

Data Index: 227588 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6956. Min Act: -0.0000

Data Index: 766568 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1792777 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4508. Min Act: -0.0000

Data Index: 587042 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3477. Min Act: -0.0000

Data Index: 822403 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1429 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.5234. Min Act: -0.0000

Data Index: 1760510 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4321. Min Act: -0.0000

Data Index: 234487 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3988. Min Act: -0.0000

Data Index: 902090 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4055. Min Act: -0.0000

Data Index: 339587 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4001. Min Act: -0.0000

Data Index: 1053554 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4550. Min Act: -0.0000

Data Index: 1056944 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1982417 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1285458 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4787. Min Act: -0.0000

Data Index: 174694 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3935. Min Act: -0.0000

Data Index: 932663 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1335006 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2873. Min Act: -0.0000

Data Index: 441494 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1354023 (The Pile)

Max Activating Token Index: 195