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

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

Neuron 4932 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: 4.4088. Min Range: -4.4088

Max Act: 4.4088. Min Act: -0.0000

Data Index: 21933 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 4.4088. Min Range: -4.4088

Max Act: 4.3319. Min Act: -0.0000

Data Index: 86736 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 4.4088. Min Range: -4.4088

Max Act: 4.2455. Min Act: -0.0000

Data Index: 580707 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.9550. Min Act: -0.0000

Data Index: 354901 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 4.4088. Min Range: -4.4088

Max Act: 4.1192. Min Act: -0.0000

Data Index: 894037 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.8793. Min Act: -0.0000

Data Index: 1066429 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.8689. Min Act: -0.0000

Data Index: 173919 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.8770. Min Act: -0.0000

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.7937. Min Act: -0.0000

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.6010. Min Act: -0.0000

Data Index: 734696 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.5035. Min Act: -0.0000

Data Index: 1161380 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.4972. Min Act: -0.0000

Data Index: 221078 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.3903. Min Act: -0.0000

Data Index: 161986 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.4860. Min Act: -0.0000

Data Index: 302422 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.5967. Min Act: -0.0000

Data Index: 532868 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.4554. Min Act: -0.0000

Data Index: 197641 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.6034. Min Act: -0.0000

Data Index: 593803 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.4110. Min Act: -0.0000

Data Index: 901489 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.5170. Min Act: -0.0000

Data Index: 481418 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 4.4088. Min Range: -4.4088

Max Act: 3.4960. Min Act: -0.0000

Data Index: 441603 (C4 (Web Text))

Max Activating Token Index: 117