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

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

Neuron 3801 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3901. Min Act: -0.0002

Data Index: 1247989 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3855. Min Act: -0.0002

Data Index: 761303 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3669. Min Act: -0.0002

Data Index: 298858 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3770. Min Act: -0.0002

Data Index: 591722 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3531. Min Act: -0.0002

Data Index: 728984 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3376. Min Act: -0.0002

Data Index: 405036 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3260. Min Act: -0.0002

Data Index: 1331070 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3233. Min Act: -0.0002

Data Index: 924253 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3312. Min Act: -0.0002

Data Index: 773374 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3241. Min Act: -0.0002

Data Index: 965281 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3126. Min Act: -0.0002

Data Index: 595910 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3227. Min Act: -0.0002

Data Index: 1315058 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3033. Min Act: -0.0002

Data Index: 638400 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3143. Min Act: -0.0002

Data Index: 198191 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3125. Min Act: -0.0002

Data Index: 825100 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2997. Min Act: -0.0002

Data Index: 633407 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3090. Min Act: -0.0002

Data Index: 630723 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3070. Min Act: -0.0002

Data Index: 1018078 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.3146. Min Act: -0.0002

Data Index: 200763 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.3901. Min Range: -0.3901

Max Act: 0.2923. Min Act: -0.0002

Data Index: 825897 (C4 (Web Text))

Max Activating Token Index: 787