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

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

Neuron 2421 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6741. Min Act: 0.0001

Data Index: 8295 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6927. Min Act: -0.0000

Data Index: 138207 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.7347. Min Act: -0.0000

Data Index: 159973 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6919. Min Act: -0.0000

Data Index: 164304 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6743. Min Act: -0.0000

Data Index: 634970 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6851. Min Act: -0.0000

Data Index: 664280 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6889. Min Act: -0.0000

Data Index: 367993 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6613. Min Act: -0.0000

Data Index: 4637 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6580. Min Act: 0.0001

Data Index: 1063973 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6568. Min Act: -0.0000

Data Index: 914109 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6471. Min Act: -0.0000

Data Index: 542340 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6657. Min Act: -0.0000

Data Index: 984188 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1199603 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1156920 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6461. Min Act: -0.0000

Data Index: 480145 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6095. Min Act: -0.0000

Data Index: 740503 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6040. Min Act: -0.0000

Data Index: 788795 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6153. Min Act: 0.0000

Data Index: 223207 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5312. Min Act: 0.0001

Data Index: 1144150 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5980. Min Act: -0.0000

Data Index: 901753 (C4 (Web Text))

Max Activating Token Index: 792