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

Dataset: The Pile

Neuron 1589 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: 1.6860. Min Range: -1.6860

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1671906 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1796272 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1900036 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4446. Min Act: -0.0000

Data Index: 73081 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1842524 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1500881 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3438. Min Act: -0.0000

Data Index: 202224 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3339. Min Act: -0.0000

Data Index: 1807133 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4212. Min Act: -0.0000

Data Index: 853374 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3208. Min Act: -0.0000

Data Index: 493959 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1450215 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1564728 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1534923 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2444. Min Act: -0.0000

Data Index: 490632 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1324776 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.3373. Min Act: -0.0000

Data Index: 1412065 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2156. Min Act: -0.0000

Data Index: 687620 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.2045. Min Act: -0.0000

Data Index: 858751 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 1.6860. Min Range: -1.6860

Max Act: 1.1803. Min Act: -0.0000

Data Index: 479371 (The Pile)

Max Activating Token Index: 792