Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3620 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.5579. Min Act: -0.0001

Data Index: 1145230 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1769. Min Act: -0.0001

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1128. Min Act: -0.0001

Data Index: 605417 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1311. Min Act: -0.0001

Data Index: 713205 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1974. Min Act: -0.0001

Data Index: 746678 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1156. Min Act: -0.0001

Data Index: 1083081 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1427. Min Act: -0.0001

Data Index: 708730 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0287. Min Act: -0.0001

Data Index: 986962 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1328. Min Act: -0.0001

Data Index: 194044 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1287. Min Act: -0.0001

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0498. Min Act: -0.0001

Data Index: 782744 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1094. Min Act: -0.0001

Data Index: 152561 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1010. Min Act: -0.0001

Data Index: 1089091 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0204. Min Act: -0.0001

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0871. Min Act: -0.0001

Data Index: 324005 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1342. Min Act: -0.0001

Data Index: 1028080 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0450. Min Act: -0.0001

Data Index: 466247 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0910. Min Act: -0.0001

Data Index: 995519 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1053742 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0385. Min Act: -0.0001

Data Index: 1132782 (C4 (Web Text))

Max Activating Token Index: 656