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

Dataset: The Pile

Neuron 4891 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: 3.0263. Min Range: -3.0263

Max Act: 3.0263. Min Act: -0.0000

Data Index: 1193311 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.5232. Min Act: -0.0000

Data Index: 360513 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1133985 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.5025. Min Act: -0.0000

Data Index: 678298 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.5577. Min Act: -0.0000

Data Index: 647209 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.5269. Min Act: -0.0000

Data Index: 664370 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.5436. Min Act: -0.0000

Data Index: 802168 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.2298. Min Act: -0.0000

Data Index: 1178710 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.2220. Min Act: -0.0000

Data Index: 1534242 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.3110. Min Act: -0.0000

Data Index: 601903 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.4226. Min Act: -0.0000

Data Index: 1446372 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.1236. Min Act: -0.0000

Data Index: 1054737 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.2160. Min Act: -0.0000

Data Index: 982086 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 3.0263. Min Range: -3.0263

Max Act: 1.9664. Min Act: -0.0000

Data Index: 537389 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1047232 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.0448. Min Act: -0.0000

Data Index: 1955417 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.1433. Min Act: -0.0000

Data Index: 984314 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.2640. Min Act: -0.0000

Data Index: 1079676 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.1147. Min Act: -0.0000

Data Index: 114157 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1889014 (The Pile)

Max Activating Token Index: 199