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

Dataset: The Pile

Neuron 3077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.7471. Min Act: -0.0000

Data Index: 517925 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1294337 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1991173 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.6090. Min Act: -0.0000

Data Index: 706230 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1560139 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.5485. Min Act: -0.0000

Data Index: 340183 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.3230. Min Act: -0.0000

Data Index: 42708 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1527138 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1559926 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4493. Min Act: -0.0000

Data Index: 601978 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1274693 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1924004 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2711. Min Act: -0.0000

Data Index: 280526 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1889476 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.1506. Min Act: -0.0000

Data Index: 1248001 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2361. Min Act: -0.0000

Data Index: 292440 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1070127 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2040. Min Act: -0.0000

Data Index: 62699 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1536888 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.7471. Min Range: -1.7471

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1874555 (The Pile)

Max Activating Token Index: 898