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

Dataset: The Pile

Neuron 3297 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: 5.2557. Min Range: -5.2557

Max Act: 4.7715. Min Act: -0.0000

Data Index: 1752938 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3439. Min Act: -0.0000

Data Index: 483089 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 5.2557. Min Range: -5.2557

Max Act: 5.2557. Min Act: -0.0000

Data Index: 1909885 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.8014. Min Act: -0.0000

Data Index: 470554 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.9625. Min Act: -0.0000

Data Index: 1189784 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.6293. Min Act: -0.0000

Data Index: 1104056 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.5454. Min Act: 0.0000

Data Index: 173135 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.7254. Min Act: -0.0000

Data Index: 1735754 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.8274. Min Act: -0.0000

Data Index: 1510987 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.2578. Min Act: -0.0000

Data Index: 1002395 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.8063. Min Act: -0.0000

Data Index: 1708369 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3874. Min Act: -0.0000

Data Index: 1434634 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.4756. Min Act: -0.0000

Data Index: 1705193 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.2730. Min Act: -0.0000

Data Index: 387843 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.0574. Min Act: -0.0000

Data Index: 1237418 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3997. Min Act: -0.0000

Data Index: 487359 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3833. Min Act: -0.0000

Data Index: 779885 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.1721. Min Act: -0.0000

Data Index: 299740 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3147. Min Act: -0.0000

Data Index: 703636 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 5.2557. Min Range: -5.2557

Max Act: 4.3464. Min Act: -0.0000

Data Index: 246790 (The Pile)

Max Activating Token Index: 358