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

Dataset: The Pile

Neuron 1541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.2495. Min Act: -0.0000

Data Index: 232427 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6289. Min Act: -0.0000

Data Index: 268724 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.0570. Min Act: -0.0000

Data Index: 131560 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6338. Min Act: -0.0000

Data Index: 1238565 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.8273. Min Act: -0.0000

Data Index: 579348 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.7386. Min Act: -0.0000

Data Index: 1379583 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5382. Min Act: -0.0000

Data Index: 1310249 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.3130. Min Act: -0.0000

Data Index: 1613350 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.1660. Min Act: -0.0000

Data Index: 390084 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.3359. Min Act: -0.0000

Data Index: 991478 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.2794. Min Act: -0.0000

Data Index: 802072 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.4227. Min Act: -0.0000

Data Index: 409483 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.2223. Min Act: -0.0000

Data Index: 138752 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.3996. Min Act: -0.0000

Data Index: 149204 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.4006. Min Act: -0.0000

Data Index: 542614 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.4030. Min Act: -0.0000

Data Index: 8544 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5353. Min Act: -0.0000

Data Index: 192030 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.0403. Min Act: -0.0000

Data Index: 1827766 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.2363. Min Act: -0.0000

Data Index: 1331176 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.3726. Min Act: -0.0000

Data Index: 1527259 (The Pile)

Max Activating Token Index: 261