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

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

Neuron 5100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3605. Min Act: -0.0000

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3481. Min Act: -0.0000

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3159. Min Act: -0.0000

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1076561 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3030. Min Act: -0.0000

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3228. Min Act: -0.0000

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2983. Min Act: -0.0000

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3374. Min Act: 0.0000

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3066. Min Act: -0.0000

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3034. Min Act: -0.0000

Data Index: 498872 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3026. Min Act: -0.0000

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2795. Min Act: -0.0000

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2778. Min Act: -0.0000

Data Index: 357583 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2786. Min Act: -0.0000

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2565. Min Act: -0.0000

Data Index: 684347 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2657. Min Act: -0.0000

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2547. Min Act: -0.0000

Data Index: 287376 (C4 (Web Text))

Max Activating Token Index: 612