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

Dataset: The Pile

Neuron 1948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5537. Min Act: -0.0000

Data Index: 117213 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1120445 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4458. Min Act: -0.0000

Data Index: 953947 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1306358 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.0548. Min Act: -0.0000

Data Index: 963342 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1735885 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3803. Min Act: -0.0000

Data Index: 343148 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3360. Min Act: -0.0000

Data Index: 632208 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1255023 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3599. Min Act: -0.0000

Data Index: 325625 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1943239 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3445. Min Act: -0.0000

Data Index: 677495 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1614486 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1056390 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1363954 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3316. Min Act: -0.0000

Data Index: 824967 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3076. Min Act: -0.0000

Data Index: 412739 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1503413 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3498. Min Act: -0.0000

Data Index: 406334 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3064. Min Act: -0.0000

Data Index: 170903 (The Pile)

Max Activating Token Index: 55