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

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

Neuron 5907 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.9787. Min Act: -0.0002

Data Index: 1085759 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.9106. Min Act: -0.0002

Data Index: 93399 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.8230. Min Act: -0.0002

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.7376. Min Act: -0.0002

Data Index: 1358144 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.7027. Min Act: -0.0002

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.7195. Min Act: -0.0002

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6729. Min Act: -0.0002

Data Index: 246861 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6116. Min Act: -0.0002

Data Index: 290616 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6541. Min Act: -0.0002

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6617. Min Act: -0.0002

Data Index: 330318 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5694. Min Act: -0.0002

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5794. Min Act: -0.0002

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5905. Min Act: -0.0002

Data Index: 62261 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6367. Min Act: -0.0002

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5456. Min Act: -0.0002

Data Index: 571329 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5780. Min Act: -0.0002

Data Index: 147598 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5226. Min Act: -0.0002

Data Index: 1305960 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5538. Min Act: -0.0002

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.5902. Min Act: -0.0002

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 3.9787. Min Range: -3.9787

Max Act: 3.6040. Min Act: -0.0002

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 343