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

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

Neuron 3721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.5167. Min Act: -0.0001

Data Index: 153284 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4423. Min Act: -0.0001

Data Index: 925693 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4355. Min Act: -0.0001

Data Index: 85872 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3947. Min Act: -0.0000

Data Index: 427692 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1325332 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1055683 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4301. Min Act: -0.0001

Data Index: 228890 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4016. Min Act: -0.0001

Data Index: 453278 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3671. Min Act: -0.0001

Data Index: 344206 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3969. Min Act: -0.0000

Data Index: 880610 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3339. Min Act: -0.0001

Data Index: 751322 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3936. Min Act: -0.0001

Data Index: 626590 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4181. Min Act: -0.0001

Data Index: 585793 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3772. Min Act: -0.0000

Data Index: 104136 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3593. Min Act: -0.0001

Data Index: 65379 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3464. Min Act: -0.0000

Data Index: 269738 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3642. Min Act: -0.0001

Data Index: 635185 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3567. Min Act: -0.0001

Data Index: 761568 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3657. Min Act: -0.0001

Data Index: 325832 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4091. Min Act: -0.0001

Data Index: 148326 (C4 (Web Text))

Max Activating Token Index: 102