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

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

Neuron 617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5137. Min Act: -0.0000

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.6540. Min Act: -0.0000

Data Index: 759505 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.6235. Min Act: -0.0000

Data Index: 1092455 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5377. Min Act: -0.0000

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5258. Min Act: -0.0000

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5253. Min Act: -0.0000

Data Index: 588767 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5168. Min Act: -0.0000

Data Index: 166016 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.4178. Min Act: -0.0000

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.5278. Min Act: -0.0000

Data Index: 347182 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.4022. Min Act: -0.0000

Data Index: 903861 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.3869. Min Act: -0.0000

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.3695. Min Act: -0.0000

Data Index: 232912 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.3477. Min Act: -0.0000

Data Index: 71770 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.3580. Min Act: -0.0000

Data Index: 474078 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.2810. Min Act: -0.0000

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.2762. Min Act: -0.0000

Data Index: 987556 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.2692. Min Act: -0.0000

Data Index: 1183101 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.1616. Min Act: -0.0000

Data Index: 739549 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.1842. Min Act: -0.0000

Data Index: 345848 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 2.6540. Min Range: -2.6540

Max Act: 2.3662. Min Act: -0.0000

Data Index: 917227 (C4 (Web Text))

Max Activating Token Index: 327