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

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

Neuron 6052 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: 8.6679. Min Range: -8.6679

Max Act: 8.6679. Min Act: -0.0000

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 8.6679. Min Range: -8.6679

Max Act: 8.2494. Min Act: -0.0000

Data Index: 737714 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 8.6679. Min Range: -8.6679

Max Act: 7.5880. Min Act: -0.0000

Data Index: 1100272 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.7159. Min Act: -0.0000

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 8.6679. Min Range: -8.6679

Max Act: 7.0230. Min Act: -0.0000

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.7439. Min Act: -0.0000

Data Index: 1218346 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.2914. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.4342. Min Act: -0.0000

Data Index: 1098870 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.4224. Min Act: -0.0000

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.4119. Min Act: -0.0000

Data Index: 132860 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.4381. Min Act: -0.0000

Data Index: 672492 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.3961. Min Act: -0.0000

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.3756. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.3616. Min Act: -0.0000

Data Index: 175516 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.0772. Min Act: -0.0000

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.2291. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 8.6679. Min Range: -8.6679

Max Act: 5.8788. Min Act: -0.0000

Data Index: 649111 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 8.6679. Min Range: -8.6679

Max Act: 5.8757. Min Act: -0.0000

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 8.6679. Min Range: -8.6679

Max Act: 6.1596. Min Act: -0.0000

Data Index: 1056608 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 8.6679. Min Range: -8.6679

Max Act: 5.9554. Min Act: -0.0000

Data Index: 920503 (C4 (Web Text))

Max Activating Token Index: 867