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

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

Neuron 3686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.9858. Min Act: 0.0000

Data Index: 1651855 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 1.1132. Min Range: -1.1132

Max Act: 1.1132. Min Act: -0.0000

Data Index: 139873 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 1.1132. Min Range: -1.1132

Max Act: 1.0379. Min Act: -0.0000

Data Index: 730447 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7734. Min Act: -0.0000

Data Index: 762076 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7728. Min Act: -0.0000

Data Index: 680836 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8276. Min Act: 0.0000

Data Index: 1271562 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6722. Min Act: -0.0000

Data Index: 380180 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1265523 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7007. Min Act: 0.0001

Data Index: 1072285 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7288. Min Act: -0.0000

Data Index: 535246 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6303. Min Act: -0.0000

Data Index: 306627 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6610. Min Act: -0.0000

Data Index: 602525 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1571982 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1268531 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6600. Min Act: 0.0000

Data Index: 554629 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6584. Min Act: -0.0000

Data Index: 48494 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6807. Min Act: -0.0000

Data Index: 499083 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6545. Min Act: -0.0000

Data Index: 707668 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6332. Min Act: -0.0000

Data Index: 674150 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.1132. Min Range: -1.1132

Max Act: 0.6487. Min Act: 0.0000

Data Index: 689994 (C4 (Web Text))

Max Activating Token Index: 836