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

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

Neuron 2150 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1334773 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6530. Min Act: -0.0000

Data Index: 860672 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1262429 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6151. Min Act: -0.0000

Data Index: 618951 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5593. Min Act: -0.0000

Data Index: 43229 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5486. Min Act: -0.0000

Data Index: 679727 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5446. Min Act: -0.0000

Data Index: 667703 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5062. Min Act: -0.0000

Data Index: 255157 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5509. Min Act: -0.0000

Data Index: 600456 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5333. Min Act: -0.0000

Data Index: 667833 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1229056 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1064597 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5044. Min Act: -0.0000

Data Index: 547969 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4734. Min Act: -0.0000

Data Index: 737217 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1307780 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1303240 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1001370 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4346. Min Act: -0.0000

Data Index: 232944 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1125332 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4658. Min Act: -0.0000

Data Index: 598170 (C4 (Web Text))

Max Activating Token Index: 182