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

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

Neuron 599 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.6933. Min Act: -0.0000

Data Index: 157588 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4986. Min Act: -0.0000

Data Index: 1100615 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4505. Min Act: -0.0000

Data Index: 1178653 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4258. Min Act: -0.0000

Data Index: 41708 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2588. Min Act: -0.0000

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2112. Min Act: -0.0000

Data Index: 1186732 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3279. Min Act: -0.0000

Data Index: 1071458 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1174998 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1288768 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1786. Min Act: -0.0000

Data Index: 161966 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2713. Min Act: -0.0000

Data Index: 52572 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2463. Min Act: -0.0000

Data Index: 1196657 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1312. Min Act: -0.0000

Data Index: 1131183 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2452. Min Act: -0.0000

Data Index: 422654 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2259. Min Act: -0.0000

Data Index: 1068132 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2123. Min Act: -0.0000

Data Index: 783996 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2040. Min Act: -0.0000

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1962. Min Act: -0.0000

Data Index: 36311 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1799. Min Act: -0.0000

Data Index: 545248 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1688. Min Act: -0.0000

Data Index: 297894 (C4 (Web Text))

Max Activating Token Index: 909