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

Dataset: The Pile

Neuron 2399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1173452 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.6571. Min Act: -0.0000

Data Index: 502130 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.6650. Min Act: -0.0000

Data Index: 322186 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1567415 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.6298. Min Act: -0.0000

Data Index: 207828 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.6186. Min Act: -0.0000

Data Index: 50526 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1211452 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5603. Min Act: -0.0000

Data Index: 617508 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1507630 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5081. Min Act: -0.0000

Data Index: 805944 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1458112 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1230934 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5037. Min Act: -0.0000

Data Index: 18757 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1374835 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1915946 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1327131 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5326. Min Act: -0.0000

Data Index: 995734 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1007568 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1006903 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.7221. Min Range: -0.7221

Max Act: 0.4638. Min Act: -0.0000

Data Index: 407971 (The Pile)

Max Activating Token Index: 968