Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5756. Min Act: -0.0000

Data Index: 941778 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1076683 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.4587. Min Act: -0.0000

Data Index: 916208 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.3267. Min Act: -0.0000

Data Index: 334990 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.2163. Min Act: -0.0000

Data Index: 774421 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1866. Min Act: -0.0000

Data Index: 599263 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1481. Min Act: -0.0000

Data Index: 852733 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.1114. Min Act: -0.0000

Data Index: 564934 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0387. Min Act: -0.0000

Data Index: 99973 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9965. Min Act: -0.0000

Data Index: 348540 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9778. Min Act: -0.0000

Data Index: 748882 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0237. Min Act: -0.0000

Data Index: 156250 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9867. Min Act: -0.0000

Data Index: 890816 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.5756. Min Range: -1.5756

Max Act: 1.0011. Min Act: -0.0000

Data Index: 841637 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9527. Min Act: -0.0000

Data Index: 589383 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9412. Min Act: -0.0000

Data Index: 144245 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1160310 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9178. Min Act: -0.0000

Data Index: 578113 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9498. Min Act: -0.0000

Data Index: 88105 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.5756. Min Range: -1.5756

Max Act: 0.9312. Min Act: -0.0000

Data Index: 579837 (C4 (Web Text))

Max Activating Token Index: 581