Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1699 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1498937 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1108255 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4715. Min Act: -0.0000

Data Index: 1465639 (Python Code)

Max Activating Token Index: 778

Text #3

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.5049. Min Act: -0.0000

Data Index: 936882 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.5623. Min Act: -0.0000

Data Index: 115163 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.5631. Min Act: 0.0000

Data Index: 488464 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.5479. Min Act: -0.0000

Data Index: 310240 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4415. Min Act: -0.0000

Data Index: 821280 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4924. Min Act: -0.0000

Data Index: 803409 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1128944 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1563605 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1287855 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.3942. Min Act: -0.0000

Data Index: 146475 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.3808. Min Act: -0.0000

Data Index: 194914 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1369062 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4571. Min Act: -0.0000

Data Index: 873575 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4610. Min Act: 0.0000

Data Index: 1145133 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4449. Min Act: -0.0000

Data Index: 196524 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.4382. Min Act: -0.0000

Data Index: 513648 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.6375. Min Range: -1.6375

Max Act: 1.5154. Min Act: 0.0000

Data Index: 143 (C4 (Web Text))

Max Activating Token Index: 978