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

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

Neuron 6138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5760. Min Act: -0.0000

Data Index: 319066 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5677. Min Act: -0.0000

Data Index: 974566 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5236. Min Act: -0.0000

Data Index: 897571 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.5061. Min Act: -0.0000

Data Index: 965521 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4839. Min Act: -0.0000

Data Index: 790757 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3982. Min Act: -0.0000

Data Index: 780997 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3894. Min Act: -0.0000

Data Index: 867274 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3318. Min Act: -0.0000

Data Index: 938110 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.4517. Min Act: -0.0000

Data Index: 680006 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3818. Min Act: -0.0000

Data Index: 1290945 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.3669. Min Act: -0.0000

Data Index: 1306986 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.1139. Min Act: -0.0000

Data Index: 1086244 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.1098. Min Act: -0.0000

Data Index: 362623 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.7426. Min Act: -0.0000

Data Index: 541638 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.8591. Min Act: -0.0000

Data Index: 1222515 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.8145. Min Act: -0.0000

Data Index: 1182623 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.9488. Min Act: -0.0000

Data Index: 265888 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.9296. Min Act: -0.0000

Data Index: 837310 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.5760. Min Range: -3.5760

Max Act: 3.0818. Min Act: -0.0000

Data Index: 284255 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.5760. Min Range: -3.5760

Max Act: 2.7601. Min Act: -0.0000

Data Index: 298397 (C4 (Web Text))

Max Activating Token Index: 13