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

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

Neuron 2500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.5167. Min Act: 0.0000

Data Index: 778397 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4768. Min Act: -0.0001

Data Index: 739920 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4359. Min Act: -0.0000

Data Index: 561802 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1217872 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4073. Min Act: -0.0001

Data Index: 352499 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3944. Min Act: -0.0000

Data Index: 931928 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3980. Min Act: -0.0000

Data Index: 466466 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3952. Min Act: -0.0000

Data Index: 564432 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3833. Min Act: -0.0000

Data Index: 539213 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3858. Min Act: 0.0000

Data Index: 412647 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3549. Min Act: -0.0000

Data Index: 163123 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3755. Min Act: -0.0000

Data Index: 595196 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3492. Min Act: -0.0000

Data Index: 472543 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1308181 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3399. Min Act: -0.0000

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3741. Min Act: -0.0000

Data Index: 898168 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3391. Min Act: -0.0000

Data Index: 875749 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3476. Min Act: -0.0000

Data Index: 455061 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3437. Min Act: -0.0000

Data Index: 148183 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3513. Min Act: -0.0000

Data Index: 88018 (C4 (Web Text))

Max Activating Token Index: 649