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

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

Neuron 3294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.3039. Min Act: -0.0000

Data Index: 52912 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1024068 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0538. Min Act: -0.0000

Data Index: 300243 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9871. Min Act: -0.0001

Data Index: 221532 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9303. Min Act: -0.0000

Data Index: 224048 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1150057 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8797. Min Act: -0.0000

Data Index: 519643 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9364. Min Act: -0.0001

Data Index: 1383864 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9389. Min Act: -0.0000

Data Index: 460930 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8762. Min Act: -0.0000

Data Index: 316242 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8252. Min Act: -0.0001

Data Index: 141794 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8676. Min Act: -0.0001

Data Index: 538770 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.7880. Min Act: -0.0001

Data Index: 634852 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8866. Min Act: -0.0001

Data Index: 685919 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8323. Min Act: -0.0000

Data Index: 476924 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.7955. Min Act: -0.0001

Data Index: 481011 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1294852 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.8065. Min Act: -0.0001

Data Index: 709539 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.7979. Min Act: -0.0000

Data Index: 119768 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.7962. Min Act: -0.0001

Data Index: 1133703 (C4 (Web Text))

Max Activating Token Index: 445