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

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

Neuron 3371 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5585. Min Range: -4.5585

Max Act: 4.5585. Min Act: -0.0000

Data Index: 537803 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 4.5585. Min Range: -4.5585

Max Act: 4.1762. Min Act: -0.0000

Data Index: 448670 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.8291. Min Act: -0.0000

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 4.5585. Min Range: -4.5585

Max Act: 4.1473. Min Act: -0.0000

Data Index: 1346653 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.9041. Min Act: -0.0000

Data Index: 867121 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.9943. Min Act: -0.0000

Data Index: 853121 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.8265. Min Act: -0.0000

Data Index: 723313 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.7240. Min Act: -0.0000

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.7262. Min Act: -0.0000

Data Index: 283728 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.6532. Min Act: -0.0000

Data Index: 770719 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.8268. Min Act: -0.0000

Data Index: 754210 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.4678. Min Act: -0.0000

Data Index: 118328 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.4271. Min Act: -0.0000

Data Index: 814239 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.7094. Min Act: -0.0000

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.3899. Min Act: -0.0000

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.3707. Min Act: -0.0000

Data Index: 971926 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.5142. Min Act: -0.0000

Data Index: 999334 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.6769. Min Act: -0.0000

Data Index: 594986 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.3560. Min Act: -0.0000

Data Index: 1321337 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.5585. Min Range: -4.5585

Max Act: 3.4682. Min Act: -0.0000

Data Index: 810380 (C4 (Web Text))

Max Activating Token Index: 350