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

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

Neuron 2442 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: 0.3986. Min Range: -0.3986

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1037245 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3892. Min Act: -0.0000

Data Index: 393022 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3637. Min Act: -0.0000

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3535. Min Act: -0.0000

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3440. Min Act: -0.0000

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3234. Min Act: -0.0000

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1359497 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3412. Min Act: -0.0000

Data Index: 347772 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3176. Min Act: -0.0000

Data Index: 177999 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1204950 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3058. Min Act: -0.0001

Data Index: 254170 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.2780. Min Act: -0.0001

Data Index: 649426 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3103. Min Act: -0.0001

Data Index: 562635 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1649465 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1643486 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1440260 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.2714. Min Act: -0.0001

Data Index: 753161 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.3986. Min Range: -0.3986

Max Act: 0.2729. Min Act: -0.0001

Data Index: 868958 (C4 (Web Text))

Max Activating Token Index: 1019