Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.4167. Min Act: -0.0001

Data Index: 91353 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3967. Min Act: -0.0001

Data Index: 20149 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3729. Min Act: -0.0001

Data Index: 259623 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3479. Min Act: -0.0001

Data Index: 868447 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3821. Min Act: -0.0001

Data Index: 635940 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3492. Min Act: -0.0001

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3480. Min Act: -0.0001

Data Index: 905309 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3608. Min Act: -0.0001

Data Index: 1017371 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3440. Min Act: -0.0001

Data Index: 428114 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1343654 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3441. Min Act: -0.0001

Data Index: 1328436 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3636. Min Act: -0.0001

Data Index: 193290 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1103797 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3354. Min Act: -0.0001

Data Index: 539603 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3291. Min Act: -0.0001

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3285. Min Act: -0.0001

Data Index: 808258 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3427. Min Act: -0.0001

Data Index: 1062300 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3067. Min Act: -0.0001

Data Index: 163852 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3205. Min Act: -0.0001

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 180