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

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

Neuron 3207 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.4674. Min Act: -0.0001

Data Index: 627371 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.4500. Min Act: -0.0001

Data Index: 810897 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3960. Min Act: -0.0001

Data Index: 236555 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3783. Min Act: -0.0001

Data Index: 1358721 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3825. Min Act: -0.0001

Data Index: 311272 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3960. Min Act: -0.0001

Data Index: 264658 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3507. Min Act: -0.0001

Data Index: 382755 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3294. Min Act: -0.0001

Data Index: 325732 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3384. Min Act: -0.0001

Data Index: 859307 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1188317 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3120. Min Act: -0.0001

Data Index: 594592 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3209. Min Act: -0.0001

Data Index: 581803 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3105. Min Act: -0.0001

Data Index: 544946 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3055. Min Act: -0.0001

Data Index: 206102 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3107. Min Act: -0.0001

Data Index: 370933 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3193. Min Act: -0.0001

Data Index: 287723 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3022. Min Act: -0.0001

Data Index: 227116 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.3006. Min Act: -0.0001

Data Index: 882516 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4674. Min Range: -0.4674

Max Act: 0.2933. Min Act: -0.0000

Data Index: 623384 (C4 (Web Text))

Max Activating Token Index: 73