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

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

Neuron 3543 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: 3.9817. Min Range: -3.9817

Max Act: 3.9817. Min Act: -0.0000

Data Index: 149424 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.6385. Min Act: -0.0000

Data Index: 442671 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.3795. Min Act: -0.0000

Data Index: 1004009 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.5348. Min Act: -0.0000

Data Index: 778074 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.4895. Min Act: -0.0000

Data Index: 1165763 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.6321. Min Act: -0.0000

Data Index: 1298425 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.4286. Min Act: -0.0000

Data Index: 560662 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.5314. Min Act: -0.0000

Data Index: 197200 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.3596. Min Act: -0.0000

Data Index: 217620 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.3339. Min Act: -0.0000

Data Index: 453052 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1349. Min Act: -0.0000

Data Index: 727652 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.4650. Min Act: -0.0000

Data Index: 1539644 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1372. Min Act: -0.0000

Data Index: 288889 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.2409. Min Act: -0.0000

Data Index: 884712 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.3442. Min Act: -0.0000

Data Index: 1306700 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1797. Min Act: -0.0000

Data Index: 193603 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1205877 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.3156. Min Act: -0.0000

Data Index: 943674 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1348. Min Act: -0.0000

Data Index: 1136730 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.9817. Min Range: -3.9817

Max Act: 3.1171. Min Act: -0.0000

Data Index: 1057454 (C4 (Web Text))

Max Activating Token Index: 268