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

Dataset: The Pile

Neuron 3396 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: 0.6458. Min Range: -0.6458

Max Act: 0.5837. Min Act: -0.0000

Data Index: 374085 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1546295 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1750496 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4932. Min Act: -0.0000

Data Index: 376548 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1450697 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5034. Min Act: -0.0000

Data Index: 663741 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1004263 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5210. Min Act: 0.0000

Data Index: 634457 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4386. Min Act: -0.0000

Data Index: 490903 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0000

Data Index: 136913 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5599. Min Act: -0.0000

Data Index: 624219 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4986. Min Act: -0.0000

Data Index: 39458 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5126. Min Act: -0.0000

Data Index: 22616 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1647187 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4384. Min Act: -0.0000

Data Index: 636452 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4165. Min Act: -0.0000

Data Index: 166126 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4572. Min Act: -0.0000

Data Index: 927120 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4367. Min Act: -0.0000

Data Index: 303393 (The Pile)

Max Activating Token Index: 943

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5138. Min Act: -0.0000

Data Index: 113174 (The Pile)

Max Activating Token Index: 924