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

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

Neuron 1429 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.2848. Min Act: -0.0001

Data Index: 361851 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.2385. Min Act: -0.0001

Data Index: 930676 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.1752. Min Act: -0.0001

Data Index: 215710 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.0943. Min Act: -0.0001

Data Index: 119311 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.1182. Min Act: -0.0001

Data Index: 712384 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.2848. Min Range: -1.2848

Max Act: 1.0240. Min Act: -0.0001

Data Index: 238256 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9580. Min Act: -0.0001

Data Index: 789036 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9312. Min Act: -0.0001

Data Index: 854392 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9759. Min Act: -0.0001

Data Index: 341058 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9209. Min Act: -0.0001

Data Index: 503049 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9122. Min Act: -0.0001

Data Index: 131416 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.8828. Min Act: -0.0001

Data Index: 189985 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9613. Min Act: -0.0001

Data Index: 178734 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.9133. Min Act: -0.0001

Data Index: 657172 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.7953. Min Act: -0.0001

Data Index: 605136 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.8989. Min Act: -0.0001

Data Index: 879957 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.8332. Min Act: -0.0001

Data Index: 126730 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.7998. Min Act: -0.0001

Data Index: 319419 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.7982. Min Act: -0.0001

Data Index: 461472 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.2848. Min Range: -1.2848

Max Act: 0.7948. Min Act: -0.0001

Data Index: 838127 (C4 (Web Text))

Max Activating Token Index: 477