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

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

Neuron 805 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6744. Min Act: -0.0001

Data Index: 753710 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6806. Min Act: -0.0001

Data Index: 158274 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6090. Min Act: -0.0001

Data Index: 7461 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6342. Min Act: -0.0001

Data Index: 779452 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6289. Min Act: -0.0001

Data Index: 592743 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6597. Min Act: -0.0001

Data Index: 827561 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6044. Min Act: -0.0001

Data Index: 801120 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5796. Min Act: -0.0001

Data Index: 440462 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6722. Min Act: -0.0001

Data Index: 296000 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6197. Min Act: -0.0001

Data Index: 360394 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5469. Min Act: -0.0001

Data Index: 415135 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5942. Min Act: -0.0001

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6099. Min Act: -0.0001

Data Index: 51095 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5743. Min Act: -0.0001

Data Index: 958071 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6125. Min Act: -0.0001

Data Index: 783942 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5653. Min Act: -0.0001

Data Index: 1140533 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5857. Min Act: -0.0001

Data Index: 983429 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5729. Min Act: -0.0001

Data Index: 147270 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5912. Min Act: -0.0001

Data Index: 1216126 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6029. Min Act: -0.0001

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 288