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

Dataset: The Pile

Neuron 2126 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: 0.4485. Min Range: -0.4485

Max Act: 0.4485. Min Act: -0.0000

Data Index: 105223 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3758. Min Act: -0.0000

Data Index: 225702 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3951. Min Act: -0.0000

Data Index: 600 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1162779 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3336. Min Act: -0.0000

Data Index: 873970 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1397402 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3050. Min Act: -0.0000

Data Index: 572069 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1383784 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1712352 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2935. Min Act: -0.0000

Data Index: 854948 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2803. Min Act: -0.0000

Data Index: 638248 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1386726 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1514439 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1190894 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1006291 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2661. Min Act: -0.0000

Data Index: 946440 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2639. Min Act: -0.0000

Data Index: 390893 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1299535 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1425605 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1721261 (The Pile)

Max Activating Token Index: 443