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

Dataset: The Pile

Neuron 3697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1297991 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3012. Min Act: -0.0000

Data Index: 811294 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1386178 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2807. Min Act: -0.0000

Data Index: 257723 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2825. Min Act: -0.0000

Data Index: 467423 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1255039 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1150297 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2860. Min Act: -0.0000

Data Index: 761652 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1271757 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2618. Min Act: -0.0000

Data Index: 16691 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2522. Min Act: -0.0000

Data Index: 657794 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2497. Min Act: -0.0000

Data Index: 435932 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2478. Min Act: -0.0000

Data Index: 855379 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2406. Min Act: -0.0000

Data Index: 31689 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1803661 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1143094 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2452. Min Act: -0.0000

Data Index: 314621 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2405. Min Act: -0.0000

Data Index: 787177 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2394. Min Act: -0.0000

Data Index: 817901 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2440. Min Act: -0.0000

Data Index: 143532 (The Pile)

Max Activating Token Index: 716