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

Dataset: The Pile

Neuron 1635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1274. Min Range: -1.1274

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1844143 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1331874 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1842508 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.6709. Min Act: -0.0000

Data Index: 726219 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1837781 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5965. Min Act: -0.0000

Data Index: 522682 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.6140. Min Act: -0.0000

Data Index: 413205 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1330376 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5646. Min Act: -0.0000

Data Index: 821350 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5932. Min Act: -0.0000

Data Index: 116787 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1078667 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1824092 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.4607. Min Act: -0.0000

Data Index: 887237 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1114660 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5155. Min Act: -0.0000

Data Index: 342591 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.4707. Min Act: -0.0000

Data Index: 332394 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1515548 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.4987. Min Act: -0.0000

Data Index: 157422 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.5015. Min Act: -0.0000

Data Index: 122678 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 1.1274. Min Range: -1.1274

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1827847 (The Pile)

Max Activating Token Index: 679