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

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

Neuron 680 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0593. Min Range: -2.0593

Max Act: 2.0593. Min Act: -0.0000

Data Index: 313352 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 2.0593. Min Range: -2.0593

Max Act: 2.0336. Min Act: -0.0000

Data Index: 579761 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.9634. Min Act: -0.0000

Data Index: 368255 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.9014. Min Act: -0.0000

Data Index: 157183 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.7380. Min Act: -0.0000

Data Index: 55727 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.8060. Min Act: -0.0000

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.9045. Min Act: -0.0000

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.7717. Min Act: -0.0000

Data Index: 901770 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.5376. Min Act: -0.0000

Data Index: 497282 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.8359. Min Act: -0.0000

Data Index: 363984 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.8371. Min Act: -0.0000

Data Index: 268345 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.7448. Min Act: -0.0000

Data Index: 491693 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.5969. Min Act: -0.0000

Data Index: 425693 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.6843. Min Act: -0.0000

Data Index: 468917 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.6549. Min Act: -0.0000

Data Index: 206481 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.5750. Min Act: -0.0000

Data Index: 239973 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1456 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.5566. Min Act: -0.0000

Data Index: 70903 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.4584. Min Act: -0.0000

Data Index: 51121 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 2.0593. Min Range: -2.0593

Max Act: 1.5758. Min Act: -0.0000

Data Index: 841249 (C4 (Web Text))

Max Activating Token Index: 894