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

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

Neuron 3333 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2146. Min Range: -4.2146

Max Act: 4.2146. Min Act: -0.0002

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 4.2146. Min Range: -4.2146

Max Act: 4.0980. Min Act: -0.0001

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.9276. Min Act: -0.0002

Data Index: 419477 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.5334. Min Act: -0.0001

Data Index: 1326907 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.9746. Min Act: -0.0001

Data Index: 413160 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.6688. Min Act: -0.0001

Data Index: 754024 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.9131. Min Act: -0.0002

Data Index: 711847 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.6122. Min Act: -0.0001

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.9731. Min Act: -0.0002

Data Index: 291415 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.7513. Min Act: -0.0001

Data Index: 1151786 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.3359. Min Act: -0.0001

Data Index: 618029 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.3438. Min Act: -0.0001

Data Index: 710541 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.4477. Min Act: -0.0001

Data Index: 274398 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.3387. Min Act: -0.0001

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.2385. Min Act: -0.0001

Data Index: 817417 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.3770. Min Act: -0.0001

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.2264. Min Act: -0.0001

Data Index: 1097736 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.4725. Min Act: -0.0001

Data Index: 1019565 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 4.2146. Min Range: -4.2146

Max Act: 3.2570. Min Act: -0.0002

Data Index: 916029 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 4.2146. Min Range: -4.2146

Max Act: 2.9416. Min Act: -0.0001

Data Index: 989098 (C4 (Web Text))

Max Activating Token Index: 321