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

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

Neuron 2628 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1720. Min Range: -6.1720

Max Act: 6.1498. Min Act: -0.0000

Data Index: 297294 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.9822. Min Act: -0.0000

Data Index: 1170769 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.9859. Min Act: -0.0000

Data Index: 152236 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 6.1720. Min Range: -6.1720

Max Act: 6.1720. Min Act: -0.0000

Data Index: 1306378 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.8705. Min Act: -0.0000

Data Index: 355410 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.7808. Min Act: -0.0000

Data Index: 649422 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.8280. Min Act: -0.0000

Data Index: 512559 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.3496. Min Act: -0.0000

Data Index: 805093 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.4958. Min Act: -0.0000

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.4717. Min Act: -0.0000

Data Index: 1177017 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5953. Min Act: -0.0000

Data Index: 228752 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.4103. Min Act: -0.0000

Data Index: 658371 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5863. Min Act: -0.0000

Data Index: 839624 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5343. Min Act: -0.0000

Data Index: 465329 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5523. Min Act: -0.0000

Data Index: 300206 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5327. Min Act: -0.0000

Data Index: 394076 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.5015. Min Act: -0.0000

Data Index: 153362 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.6753. Min Act: -0.0000

Data Index: 32772 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.1254. Min Act: -0.0000

Data Index: 87866 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 6.1720. Min Range: -6.1720

Max Act: 5.2589. Min Act: -0.0000

Data Index: 676633 (C4 (Web Text))

Max Activating Token Index: 927