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

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

Neuron 4020 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4862. Min Act: -0.0000

Data Index: 318241 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.5170. Min Act: -0.0000

Data Index: 733439 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.5187. Min Act: -0.0000

Data Index: 847451 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4602. Min Act: -0.0000

Data Index: 810483 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4600. Min Act: -0.0000

Data Index: 908502 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4506. Min Act: -0.0000

Data Index: 516007 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4501. Min Act: -0.0000

Data Index: 19460 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4348. Min Act: -0.0000

Data Index: 92173 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.4054. Min Act: -0.0000

Data Index: 280964 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3906. Min Act: -0.0000

Data Index: 312711 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3991. Min Act: -0.0000

Data Index: 606297 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1121820 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3636. Min Act: -0.0000

Data Index: 779228 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3092. Min Act: -0.0000

Data Index: 75559 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3900. Min Act: -0.0000

Data Index: 481136 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3372. Min Act: -0.0000

Data Index: 816015 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1015092 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1197084 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3766. Min Act: -0.0000

Data Index: 160808 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.5187. Min Range: -0.5187

Max Act: 0.3532. Min Act: -0.0000

Data Index: 265827 (C4 (Web Text))

Max Activating Token Index: 698