Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 573 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1319428 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1141180 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1593751 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1597581 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1290954 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4854. Min Act: -0.0000

Data Index: 485078 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1109920 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4493. Min Act: -0.0000

Data Index: 324072 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4596. Min Act: -0.0000

Data Index: 807241 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1148539 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4458. Min Act: -0.0000

Data Index: 908764 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4461. Min Act: -0.0000

Data Index: 827771 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4423. Min Act: -0.0000

Data Index: 541835 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4279. Min Act: -0.0000

Data Index: 664549 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4273. Min Act: -0.0000

Data Index: 997640 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4384. Min Act: -0.0000

Data Index: 957900 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1853094 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1955800 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3808. Min Act: -0.0000

Data Index: 652828 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3963. Min Act: -0.0000

Data Index: 919694 (The Pile)

Max Activating Token Index: 763