Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2893. Min Range: -2.2893

Max Act: 2.2893. Min Act: -0.0000

Data Index: 721171 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.2893. Min Range: -2.2893

Max Act: 2.1014. Min Act: -0.0000

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.9461. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.4969. Min Act: -0.0000

Data Index: 372536 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1365159 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1388276 (Python Code)

Max Activating Token Index: 559

Text #7

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3248. Min Act: -0.0000

Data Index: 905986 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.4301. Min Act: -0.0000

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1473493 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1631928 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1629566 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1439159 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.2850. Min Act: -0.0000

Data Index: 410466 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.2693. Min Act: -0.0000

Data Index: 957021 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.1213. Min Act: -0.0000

Data Index: 514097 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1526703 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1366854 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.1552. Min Act: -0.0000

Data Index: 958249 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 2.2893. Min Range: -2.2893

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1618334 (Python Code)

Max Activating Token Index: 718