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

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

Neuron 4310 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1636020 (Python Code)

Max Activating Token Index: 1008

Text #1

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1400958 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1087396 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4553. Min Act: -0.0000

Data Index: 56607 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4859. Min Act: -0.0000

Data Index: 646483 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4462. Min Act: -0.0000

Data Index: 530079 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4550. Min Act: -0.0000

Data Index: 625368 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1297940 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1595319 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4027. Min Act: -0.0000

Data Index: 92978 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1430460 (Python Code)

Max Activating Token Index: 487

Text #11

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1552281 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1529538 (Python Code)

Max Activating Token Index: 829

Text #13

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1443458 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1454084 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4079. Min Act: -0.0000

Data Index: 763241 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1410616 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4323. Min Act: -0.0000

Data Index: 575639 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1398162 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1518954 (Python Code)

Max Activating Token Index: 455