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

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

Neuron 1102 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4527. Min Act: -0.0000

Data Index: 713039 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3343. Min Act: -0.0000

Data Index: 477694 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3254. Min Act: -0.0000

Data Index: 791236 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3136. Min Act: -0.0000

Data Index: 84666 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3179. Min Act: -0.0000

Data Index: 621695 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3070. Min Act: -0.0000

Data Index: 90288 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2991. Min Act: -0.0000

Data Index: 213077 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1055468 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1060912 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2940. Min Act: -0.0000

Data Index: 520814 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2958. Min Act: -0.0000

Data Index: 626979 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1172316 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2974. Min Act: -0.0000

Data Index: 521159 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2777. Min Act: -0.0000

Data Index: 920763 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1164416 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2565. Min Act: -0.0000

Data Index: 767825 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2806. Min Act: 0.0000

Data Index: 656896 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2841. Min Act: -0.0000

Data Index: 343699 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2603. Min Act: -0.0000

Data Index: 819982 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1345618 (C4 (Web Text))

Max Activating Token Index: 469