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

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

Neuron 3250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.2197. Min Act: -0.0000

Data Index: 973190 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.3099. Min Act: -0.0000

Data Index: 774811 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.3099. Min Range: -1.3099

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1188877 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1005005 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9717. Min Act: -0.0000

Data Index: 20555 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1094687 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8672. Min Act: -0.0000

Data Index: 325383 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9457. Min Act: -0.0000

Data Index: 989656 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1231968 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8785. Min Act: -0.0000

Data Index: 483255 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8479. Min Act: -0.0000

Data Index: 440521 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8712. Min Act: -0.0000

Data Index: 62824 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.9268. Min Act: -0.0000

Data Index: 89663 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8489. Min Act: -0.0000

Data Index: 696902 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1257623 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1277276 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.7284. Min Act: -0.0000

Data Index: 681303 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.7839. Min Act: -0.0000

Data Index: 382568 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.8337. Min Act: -0.0000

Data Index: 920651 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.3099. Min Range: -1.3099

Max Act: 0.7456. Min Act: -0.0000

Data Index: 385757 (C4 (Web Text))

Max Activating Token Index: 106