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

Dataset: The Pile

Neuron 1341 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: 0.6507. Min Range: -0.6507

Max Act: 0.6507. Min Act: -0.0000

Data Index: 552586 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1384943 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5104. Min Act: -0.0000

Data Index: 829258 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5357. Min Act: -0.0000

Data Index: 197840 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1887827 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1937018 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4963. Min Act: -0.0000

Data Index: 760924 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1383711 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4440. Min Act: -0.0000

Data Index: 326354 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1872971 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1423247 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4690. Min Act: -0.0000

Data Index: 568563 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1607167 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1501358 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1942319 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4350. Min Act: -0.0000

Data Index: 333761 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1109923 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1294203 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1052445 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1788934 (The Pile)

Max Activating Token Index: 212