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

Dataset: The Pile

Neuron 1656 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: 3.4168. Min Range: -3.4168

Max Act: 3.2906. Min Act: -0.0000

Data Index: 1138335 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 3.4168. Min Range: -3.4168

Max Act: 3.4168. Min Act: -0.0000

Data Index: 344143 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 3.4168. Min Range: -3.4168

Max Act: 3.1234. Min Act: -0.0000

Data Index: 1097594 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 3.4168. Min Range: -3.4168

Max Act: 3.3687. Min Act: -0.0000

Data Index: 1810710 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 3.4168. Min Range: -3.4168

Max Act: 2.3129. Min Act: -0.0000

Data Index: 1667590 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.4168. Min Range: -3.4168

Max Act: 2.0734. Min Act: -0.0000

Data Index: 431645 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.9897. Min Act: -0.0000

Data Index: 1363327 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.9605. Min Act: -0.0000

Data Index: 1730046 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1444295 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.8723. Min Act: -0.0000

Data Index: 1930056 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.8001. Min Act: -0.0000

Data Index: 941216 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.8352. Min Act: -0.0000

Data Index: 856837 (The Pile)

Max Activating Token Index: 320

Text #12

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.9529. Min Act: -0.0000

Data Index: 1366734 (The Pile)

Max Activating Token Index: 873

Text #13

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1589808 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1602107 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.7647. Min Act: -0.0000

Data Index: 990390 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.6640. Min Act: -0.0000

Data Index: 226337 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1704640 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.7430. Min Act: -0.0000

Data Index: 1910494 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 3.4168. Min Range: -3.4168

Max Act: 1.7410. Min Act: -0.0000

Data Index: 310049 (The Pile)

Max Activating Token Index: 402