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

Dataset: The Pile

Neuron 1983 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7406. Min Act: -0.0000

Data Index: 849378 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6204. Min Act: -0.0000

Data Index: 740832 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1194365 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6086. Min Act: -0.0000

Data Index: 759241 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1792295 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5698. Min Act: -0.0000

Data Index: 269395 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1421786 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1827025 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5292. Min Act: -0.0000

Data Index: 278395 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1451191 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1670611 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1726944 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1053157 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1186575 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1146619 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5815. Min Act: -0.0000

Data Index: 161519 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5253. Min Act: -0.0000

Data Index: 465938 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1422815 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1233580 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1538905 (The Pile)

Max Activating Token Index: 584