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

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

Neuron 5044 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.4541. Min Range: -11.4541

Max Act: 11.4541. Min Act: -0.0000

Data Index: 852157 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.6584. Min Act: -0.0000

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1282695 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1274904 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.5450. Min Act: -0.0000

Data Index: 166027 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3833. Min Act: -0.0000

Data Index: 882571 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4759. Min Act: -0.0000

Data Index: 517774 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3437. Min Act: -0.0000

Data Index: 38141 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4334. Min Act: -0.0000

Data Index: 816312 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1078825 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4241. Min Act: -0.0000

Data Index: 988150 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1349816 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.4644. Min Act: -0.0000

Data Index: 936227 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3675. Min Act: -0.0000

Data Index: 657578 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3278. Min Act: -0.0000

Data Index: 450753 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3693. Min Act: -0.0000

Data Index: 496812 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3701. Min Act: -0.0000

Data Index: 7822 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3811. Min Act: -0.0000

Data Index: 618111 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 11.4541. Min Range: -11.4541

Max Act: 0.3689. Min Act: -0.0000

Data Index: 600679 (C4 (Web Text))

Max Activating Token Index: 852