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

Dataset: The Pile

Neuron 3580 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: 0.6448. Min Range: -0.6448

Max Act: 0.6448. Min Act: -0.0000

Data Index: 810783 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1338668 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5661. Min Act: -0.0000

Data Index: 288430 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5454. Min Act: -0.0000

Data Index: 839227 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1577397 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.4474. Min Act: -0.0000

Data Index: 674933 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1504482 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1091629 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.3558. Min Act: -0.0000

Data Index: 732706 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2916. Min Act: -0.0000

Data Index: 797715 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2803. Min Act: -0.0000

Data Index: 843291 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1786715 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2549. Min Act: -0.0000

Data Index: 503238 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2162. Min Act: -0.0000

Data Index: 473422 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1930538 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.1890. Min Act: -0.0000

Data Index: 936427 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1752352 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1757130 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1389213 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1091025 (The Pile)

Max Activating Token Index: 812