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

Dataset: The Pile

Neuron 167 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: 1.0943. Min Range: -1.0943

Max Act: 1.0943. Min Act: -0.0000

Data Index: 845935 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1772107 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.9447. Min Act: -0.0000

Data Index: 773650 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8304. Min Act: -0.0000

Data Index: 933602 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1885155 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1080045 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7815. Min Act: -0.0000

Data Index: 109958 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1594144 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1313574 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7915. Min Act: -0.0000

Data Index: 242711 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7535. Min Act: -0.0000

Data Index: 256042 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8201. Min Act: -0.0000

Data Index: 406548 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7464. Min Act: -0.0000

Data Index: 630981 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1940502 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7747. Min Act: -0.0000

Data Index: 418735 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7424. Min Act: -0.0000

Data Index: 700635 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1516853 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1608892 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1139853 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1987973 (The Pile)

Max Activating Token Index: 515