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

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

Neuron 43 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1095228 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0126. Min Act: -0.0000

Data Index: 461415 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0572. Min Act: -0.0000

Data Index: 822935 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8644. Min Act: -0.0000

Data Index: 675246 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9227. Min Act: -0.0000

Data Index: 967315 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8841. Min Act: -0.0000

Data Index: 594779 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9569. Min Act: -0.0000

Data Index: 244678 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9118. Min Act: -0.0000

Data Index: 982124 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8457. Min Act: -0.0001

Data Index: 129829 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9244. Min Act: -0.0001

Data Index: 732541 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9070. Min Act: -0.0001

Data Index: 41439 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8630. Min Act: -0.0001

Data Index: 231682 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8532. Min Act: -0.0000

Data Index: 31412 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1144541 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8961. Min Act: -0.0000

Data Index: 396563 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8659. Min Act: -0.0000

Data Index: 26985 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8856. Min Act: -0.0000

Data Index: 916913 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8268. Min Act: -0.0000

Data Index: 351027 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1171506 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8371. Min Act: -0.0000

Data Index: 943993 (C4 (Web Text))

Max Activating Token Index: 814