Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3211 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1084771 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4484. Min Act: -0.0000

Data Index: 853458 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1518683 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1468648 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1231652 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1507190 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4402. Min Act: -0.0000

Data Index: 160216 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1947867 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4137. Min Act: -0.0000

Data Index: 663549 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3935. Min Act: -0.0000

Data Index: 26395 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3631. Min Act: -0.0000

Data Index: 873387 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1363142 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1591202 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4085. Min Act: -0.0000

Data Index: 435055 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1849071 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1173030 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3595. Min Act: -0.0000

Data Index: 854288 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3709. Min Act: -0.0000

Data Index: 618234 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3556. Min Act: -0.0000

Data Index: 988580 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.3583. Min Act: -0.0000

Data Index: 940336 (The Pile)

Max Activating Token Index: 1011