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

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

Neuron 2563 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1131. Min Range: -1.1131

Max Act: 1.1131. Min Act: -0.0001

Data Index: 79749 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.1131. Min Range: -1.1131

Max Act: 1.0753. Min Act: -0.0001

Data Index: 873719 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8574. Min Act: -0.0001

Data Index: 258709 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9491. Min Act: -0.0001

Data Index: 425717 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9575. Min Act: -0.0001

Data Index: 1187531 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9439. Min Act: -0.0001

Data Index: 731483 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1106965 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1073516 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8648. Min Act: -0.0001

Data Index: 965359 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8728. Min Act: -0.0001

Data Index: 586504 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8759. Min Act: -0.0001

Data Index: 515444 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7904. Min Act: -0.0001

Data Index: 186363 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1104630 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8440. Min Act: -0.0001

Data Index: 200026 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7588. Min Act: -0.0001

Data Index: 511371 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8008. Min Act: -0.0001

Data Index: 1200072 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7563. Min Act: -0.0001

Data Index: 1063487 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7664. Min Act: -0.0001

Data Index: 260286 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7404. Min Act: -0.0001

Data Index: 325635 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7892. Min Act: -0.0001

Data Index: 304592 (C4 (Web Text))

Max Activating Token Index: 449