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

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

Neuron 1282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.8158. Min Act: -0.0000

Data Index: 324974 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.9058. Min Act: -0.0000

Data Index: 849142 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.8346. Min Act: -0.0000

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7880. Min Act: -0.0001

Data Index: 80320 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.8904. Min Act: -0.0001

Data Index: 813205 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6760. Min Act: -0.0000

Data Index: 255734 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.8822. Min Act: -0.0000

Data Index: 17271 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7815. Min Act: -0.0000

Data Index: 2278 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7737. Min Act: -0.0000

Data Index: 338722 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7600. Min Act: -0.0000

Data Index: 527599 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1338199 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7849. Min Act: -0.0000

Data Index: 854012 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7350. Min Act: -0.0000

Data Index: 842021 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7490. Min Act: -0.0001

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7238. Min Act: -0.0001

Data Index: 38045 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6372. Min Act: -0.0000

Data Index: 815947 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6929. Min Act: -0.0000

Data Index: 90495 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6789. Min Act: -0.0000

Data Index: 391514 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7117. Min Act: -0.0000

Data Index: 363335 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7683. Min Act: -0.0001

Data Index: 71279 (C4 (Web Text))

Max Activating Token Index: 962