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

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

Neuron 3806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.8358. Min Act: -0.0002

Data Index: 629818 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.8151. Min Act: -0.0002

Data Index: 749531 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7341. Min Act: -0.0002

Data Index: 481654 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7424. Min Act: -0.0002

Data Index: 681997 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6889. Min Act: -0.0002

Data Index: 930133 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7168. Min Act: -0.0002

Data Index: 1027059 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6967. Min Act: -0.0002

Data Index: 761956 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.7004. Min Act: -0.0002

Data Index: 199636 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6506. Min Act: -0.0002

Data Index: 1185670 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6624. Min Act: -0.0002

Data Index: 1257528 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6593. Min Act: -0.0002

Data Index: 1015443 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6430. Min Act: -0.0002

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6725. Min Act: -0.0002

Data Index: 165281 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6088. Min Act: -0.0002

Data Index: 354040 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6619. Min Act: -0.0002

Data Index: 964737 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6256. Min Act: -0.0002

Data Index: 1190222 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6039. Min Act: -0.0002

Data Index: 959830 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6040. Min Act: -0.0002

Data Index: 383667 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6343. Min Act: -0.0002

Data Index: 254695 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.8358. Min Range: -0.8358

Max Act: 0.6068. Min Act: -0.0002

Data Index: 585554 (C4 (Web Text))

Max Activating Token Index: 466