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

Dataset: The Pile

Neuron 4084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1226352 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3962. Min Act: -0.0000

Data Index: 791398 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1465431 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1827765 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3151. Min Act: -0.0000

Data Index: 328791 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1368156 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1238896 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2936. Min Act: -0.0000

Data Index: 670423 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1823845 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2907. Min Act: -0.0001

Data Index: 645733 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3008. Min Act: -0.0000

Data Index: 692032 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1597279 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1190979 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2795. Min Act: -0.0000

Data Index: 506278 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2826. Min Act: -0.0000

Data Index: 359303 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1670074 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2699. Min Act: -0.0000

Data Index: 892716 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2725. Min Act: -0.0000

Data Index: 56292 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2525. Min Act: -0.0000

Data Index: 523986 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.2772. Min Act: -0.0000

Data Index: 999864 (The Pile)

Max Activating Token Index: 141