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

Dataset: The Pile

Neuron 390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1127. Min Range: -1.1127

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1982691 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 1.1127. Min Range: -1.1127

Max Act: 1.0212. Min Act: -0.0000

Data Index: 570228 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1314641 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8860. Min Act: 0.0000

Data Index: 487444 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.9230. Min Act: -0.0000

Data Index: 104629 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1980367 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8881. Min Act: -0.0000

Data Index: 899464 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1182669 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.9053. Min Act: -0.0000

Data Index: 25529 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1036338 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7850. Min Act: -0.0000

Data Index: 644160 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1596269 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8312. Min Act: -0.0000

Data Index: 741790 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8435. Min Act: -0.0000

Data Index: 895249 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7955. Min Act: 0.0000

Data Index: 1771034 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1468989 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1064018 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8797. Min Act: -0.0000

Data Index: 968258 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8461. Min Act: -0.0000

Data Index: 467877 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1966114 (The Pile)

Max Activating Token Index: 694