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

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

Neuron 3659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.7697. Min Act: -0.0002

Data Index: 482257 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.6514. Min Act: -0.0002

Data Index: 1355289 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5370. Min Act: -0.0002

Data Index: 1356824 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.6252. Min Act: -0.0002

Data Index: 979317 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.7347. Min Act: -0.0002

Data Index: 1207306 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.6494. Min Act: -0.0002

Data Index: 219791 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5285. Min Act: -0.0002

Data Index: 1132082 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.7146. Min Act: -0.0002

Data Index: 351391 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5931. Min Act: -0.0002

Data Index: 702997 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5071. Min Act: -0.0002

Data Index: 773521 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4664. Min Act: -0.0002

Data Index: 212220 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5679. Min Act: -0.0002

Data Index: 1084148 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4179. Min Act: -0.0002

Data Index: 863161 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4414. Min Act: -0.0002

Data Index: 1210352 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.5060. Min Act: -0.0002

Data Index: 112783 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.6588. Min Act: -0.0002

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3807. Min Act: -0.0002

Data Index: 196419 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3643. Min Act: -0.0002

Data Index: 246707 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.3497. Min Act: -0.0002

Data Index: 959377 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.7697. Min Range: -1.7697

Max Act: 1.4706. Min Act: -0.0002

Data Index: 1215852 (C4 (Web Text))

Max Activating Token Index: 694