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

Dataset: The Pile

Neuron 3929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1774167 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1086135 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1959124 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1466375 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6339. Min Act: -0.0000

Data Index: 319784 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1803824 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1347133 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6051. Min Act: -0.0000

Data Index: 4166 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5644. Min Act: -0.0000

Data Index: 562152 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1437796 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1250360 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5594. Min Act: -0.0000

Data Index: 88332 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1095202 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5798. Min Act: -0.0000

Data Index: 200188 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1735474 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1701437 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5312. Min Act: -0.0000

Data Index: 148408 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5435. Min Act: -0.0000

Data Index: 988088 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5579. Min Act: -0.0000

Data Index: 340680 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1625346 (The Pile)

Max Activating Token Index: 345