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

Dataset: The Pile

Neuron 3207 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: 0.7068. Min Range: -0.7068

Max Act: 0.6729. Min Act: -0.0000

Data Index: 637074 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1029919 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1581835 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5872. Min Act: -0.0000

Data Index: 334734 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5997. Min Act: -0.0000

Data Index: 182693 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1327869 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1373170 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1326183 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5837. Min Act: -0.0000

Data Index: 786805 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.6194. Min Act: -0.0000

Data Index: 504164 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5475. Min Act: -0.0000

Data Index: 633176 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1768551 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5393. Min Act: -0.0000

Data Index: 499156 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5493. Min Act: -0.0000

Data Index: 919862 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1085679 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.5128. Min Act: -0.0000

Data Index: 435425 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4570. Min Act: -0.0000

Data Index: 361907 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4940. Min Act: -0.0000

Data Index: 578544 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4917. Min Act: -0.0000

Data Index: 688841 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 0.7068. Min Range: -0.7068

Max Act: 0.4872. Min Act: -0.0000

Data Index: 51514 (The Pile)

Max Activating Token Index: 414