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

Dataset: The Pile

Neuron 2637 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2205. Min Range: -5.2205

Max Act: 5.2205. Min Act: -0.0000

Data Index: 1679521 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.2087. Min Act: -0.0000

Data Index: 1822097 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.1325. Min Act: -0.0000

Data Index: 1917680 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 5.2205. Min Range: -5.2205

Max Act: 4.0444. Min Act: -0.0000

Data Index: 1202613 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 5.2205. Min Range: -5.2205

Max Act: 3.6324. Min Act: -0.0000

Data Index: 1550919 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 5.2205. Min Range: -5.2205

Max Act: 3.4503. Min Act: -0.0000

Data Index: 815578 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 5.2205. Min Range: -5.2205

Max Act: 3.5090. Min Act: -0.0000

Data Index: 1246639 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 5.2205. Min Range: -5.2205

Max Act: 3.2520. Min Act: -0.0000

Data Index: 520199 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 5.2205. Min Range: -5.2205

Max Act: 3.0038. Min Act: -0.0000

Data Index: 975502 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 5.2205. Min Range: -5.2205

Max Act: 2.0816. Min Act: -0.0000

Data Index: 724932 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.9921. Min Act: -0.0000

Data Index: 476132 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.8342. Min Act: -0.0000

Data Index: 1921998 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.8973. Min Act: -0.0000

Data Index: 515968 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1483565 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1091883 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1127298 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1447419 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1728421 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.3881. Min Act: -0.0000

Data Index: 158260 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 5.2205. Min Range: -5.2205

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1752782 (The Pile)

Max Activating Token Index: 819