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

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

Neuron 4472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.9547. Min Act: -0.0000

Data Index: 870266 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1130483 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5846. Min Act: -0.0000

Data Index: 832113 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5997. Min Act: -0.0000

Data Index: 302062 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5431. Min Act: -0.0000

Data Index: 964970 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5657. Min Act: -0.0000

Data Index: 704301 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5167. Min Act: -0.0000

Data Index: 791735 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5384. Min Act: -0.0000

Data Index: 72859 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1112769 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4788. Min Act: -0.0000

Data Index: 73848 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4818. Min Act: -0.0000

Data Index: 91516 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4628. Min Act: -0.0000

Data Index: 642087 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4811. Min Act: -0.0000

Data Index: 515796 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4701. Min Act: -0.0000

Data Index: 620077 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4904. Min Act: -0.0000

Data Index: 652976 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4614. Min Act: -0.0000

Data Index: 600965 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4694. Min Act: -0.0000

Data Index: 960678 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4681. Min Act: -0.0000

Data Index: 58633 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4375. Min Act: -0.0000

Data Index: 848634 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.9547. Min Range: -0.9547

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1261698 (C4 (Web Text))

Max Activating Token Index: 967