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

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

Neuron 3700 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: 0.4649. Min Range: -0.4649

Max Act: 0.4649. Min Act: -0.0000

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.4169. Min Act: -0.0000

Data Index: 950899 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3845. Min Act: -0.0000

Data Index: 668139 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.4027. Min Act: -0.0000

Data Index: 869732 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3793. Min Act: -0.0000

Data Index: 791819 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1274037 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1292721 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3587. Min Act: -0.0000

Data Index: 910597 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3574. Min Act: -0.0000

Data Index: 587014 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3587. Min Act: -0.0000

Data Index: 351373 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3659. Min Act: -0.0001

Data Index: 1310695 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3395. Min Act: -0.0000

Data Index: 7931 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3548. Min Act: -0.0000

Data Index: 766141 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1226019 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3111. Min Act: -0.0000

Data Index: 505436 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3295. Min Act: -0.0000

Data Index: 716856 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3193. Min Act: -0.0000

Data Index: 407468 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3202. Min Act: -0.0000

Data Index: 3290 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3134. Min Act: -0.0000

Data Index: 256160 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3398. Min Act: -0.0000

Data Index: 664420 (C4 (Web Text))

Max Activating Token Index: 738