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

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

Neuron 817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.8408. Min Act: -0.0000

Data Index: 1244842 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.9125. Min Act: -0.0000

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.6695. Min Act: -0.0000

Data Index: 840944 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5911. Min Act: -0.0000

Data Index: 739715 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.7224. Min Act: -0.0000

Data Index: 114622 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1078547 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.8154. Min Act: -0.0000

Data Index: 506012 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.6485. Min Act: -0.0000

Data Index: 462991 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.6659. Min Act: -0.0000

Data Index: 211961 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.4435. Min Act: -0.0000

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5722. Min Act: -0.0000

Data Index: 1269148 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5640. Min Act: -0.0000

Data Index: 685147 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5631. Min Act: -0.0000

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5160. Min Act: -0.0000

Data Index: 29012 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5029. Min Act: -0.0000

Data Index: 286964 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1084897 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.3417. Min Act: -0.0000

Data Index: 589915 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.5578. Min Act: -0.0000

Data Index: 54893 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.3156. Min Act: -0.0000

Data Index: 244503 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.8408. Min Range: -3.8408

Max Act: 2.3188. Min Act: -0.0000

Data Index: 1017061 (C4 (Web Text))

Max Activating Token Index: 227