Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3129 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3616. Min Act: -0.0000

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3333. Min Act: -0.0001

Data Index: 982493 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3070. Min Act: -0.0001

Data Index: 916137 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2973. Min Act: -0.0001

Data Index: 527181 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1046145 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2797. Min Act: -0.0001

Data Index: 828641 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2992. Min Act: -0.0001

Data Index: 518786 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3091. Min Act: -0.0001

Data Index: 13524 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1120837 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1027324 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2740. Min Act: -0.0000

Data Index: 231675 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2809. Min Act: -0.0000

Data Index: 204167 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1132373 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2741. Min Act: -0.0001

Data Index: 600293 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2541. Min Act: -0.0000

Data Index: 920163 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2572. Min Act: -0.0001

Data Index: 638969 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1082011 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2536. Min Act: -0.0000

Data Index: 275156 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2544. Min Act: -0.0001

Data Index: 343329 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2453. Min Act: -0.0000

Data Index: 874787 (C4 (Web Text))

Max Activating Token Index: 446