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

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

Neuron 3665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1149487 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.1575. Min Act: -0.0000

Data Index: 311582 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0092. Min Act: -0.0000

Data Index: 199648 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9938. Min Act: -0.0000

Data Index: 443949 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.0016. Min Act: -0.0000

Data Index: 480773 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.4027. Min Range: -1.4027

Max Act: 1.1035. Min Act: -0.0000

Data Index: 521327 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9626. Min Act: -0.0000

Data Index: 21534 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9785. Min Act: -0.0000

Data Index: 311513 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9083. Min Act: -0.0000

Data Index: 4256 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9631. Min Act: -0.0000

Data Index: 626993 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9446. Min Act: -0.0000

Data Index: 759549 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9225. Min Act: -0.0000

Data Index: 45367 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9524. Min Act: -0.0000

Data Index: 128520 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1133121 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1269204 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.9373. Min Act: -0.0000

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8375. Min Act: -0.0000

Data Index: 647971 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8866. Min Act: -0.0000

Data Index: 578303 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.4027. Min Range: -1.4027

Max Act: 0.8503. Min Act: -0.0000

Data Index: 912494 (C4 (Web Text))

Max Activating Token Index: 720