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

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

Neuron 2376 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: 0.4028. Min Range: -0.4028

Max Act: 0.4028. Min Act: -0.0001

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1295025 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1015251 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2835. Min Act: -0.0000

Data Index: 162619 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2351. Min Act: 0.0000

Data Index: 140009 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1148655 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1919. Min Act: -0.0000

Data Index: 796195 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1256580 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1925. Min Act: -0.0001

Data Index: 691355 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1878. Min Act: -0.0001

Data Index: 1143810 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1866. Min Act: -0.0001

Data Index: 443685 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1763. Min Act: -0.0000

Data Index: 32331 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1697. Min Act: -0.0001

Data Index: 63861 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1130092 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1443. Min Act: -0.0001

Data Index: 158651 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1493. Min Act: -0.0001

Data Index: 234815 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1535. Min Act: -0.0001

Data Index: 528589 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1524. Min Act: -0.0001

Data Index: 88073 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1483. Min Act: -0.0000

Data Index: 441041 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.4028. Min Range: -0.4028

Max Act: 0.1477. Min Act: -0.0000

Data Index: 353107 (C4 (Web Text))

Max Activating Token Index: 616