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

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

Neuron 1060 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3470. Min Act: -0.0000

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1025291 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2325. Min Act: -0.0000

Data Index: 438672 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1171217 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2307. Min Act: -0.0001

Data Index: 876904 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2292. Min Act: -0.0000

Data Index: 720396 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2108. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2141. Min Act: -0.0001

Data Index: 775833 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1246189 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2303. Min Act: -0.0001

Data Index: 637036 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2119. Min Act: -0.0000

Data Index: 878015 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2093. Min Act: -0.0001

Data Index: 548995 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2126. Min Act: -0.0001

Data Index: 301649 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1235349 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2053. Min Act: -0.0001

Data Index: 538383 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2120. Min Act: -0.0001

Data Index: 93388 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1309627 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2018. Min Act: -0.0001

Data Index: 26223 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2067. Min Act: -0.0000

Data Index: 44673 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.1962. Min Act: -0.0000

Data Index: 405488 (C4 (Web Text))

Max Activating Token Index: 935