Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2828 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.3263. Min Act: -0.0000

Data Index: 793623 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.4119. Min Act: -0.0000

Data Index: 135802 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.4091. Min Act: -0.0000

Data Index: 507956 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.2346. Min Act: -0.0000

Data Index: 894754 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.3523. Min Act: -0.0000

Data Index: 865933 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.3479. Min Act: -0.0000

Data Index: 569834 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.2992. Min Act: -0.0000

Data Index: 387994 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.2634. Min Act: -0.0000

Data Index: 981176 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.2785. Min Act: -0.0000

Data Index: 721638 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1136832 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1934. Min Act: -0.0000

Data Index: 995617 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1079339 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.2709. Min Act: -0.0000

Data Index: 708348 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1633. Min Act: -0.0000

Data Index: 789068 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1837. Min Act: -0.0000

Data Index: 282513 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1042. Min Act: -0.0000

Data Index: 968516 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.0933. Min Act: -0.0000

Data Index: 853180 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1546. Min Act: -0.0000

Data Index: 66701 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.0499. Min Act: -0.0000

Data Index: 982513 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.4119. Min Range: -1.4119

Max Act: 1.1907. Min Act: -0.0000

Data Index: 62899 (C4 (Web Text))

Max Activating Token Index: 269