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

Dataset: The Pile

Neuron 4747 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: 4.0060. Min Range: -4.0060

Max Act: 3.4817. Min Act: -0.0000

Data Index: 1149522 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 4.0060. Min Range: -4.0060

Max Act: 4.0060. Min Act: -0.0000

Data Index: 1063632 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.7853. Min Act: -0.0000

Data Index: 185776 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.5016. Min Act: -0.0000

Data Index: 1033029 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.4196. Min Act: -0.0000

Data Index: 1417422 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.5306. Min Act: -0.0000

Data Index: 647835 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.3776. Min Act: -0.0000

Data Index: 729684 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.0613. Min Act: -0.0000

Data Index: 1294282 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.0323. Min Act: -0.0000

Data Index: 220918 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.3193. Min Act: -0.0000

Data Index: 926361 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 4.0060. Min Range: -4.0060

Max Act: 2.6701. Min Act: -0.0000

Data Index: 620109 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.0491. Min Act: -0.0000

Data Index: 525421 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.3369. Min Act: -0.0000

Data Index: 1630223 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.1593. Min Act: -0.0000

Data Index: 1374892 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.2971. Min Act: -0.0000

Data Index: 989821 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1205612 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.2558. Min Act: -0.0000

Data Index: 252079 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.1117. Min Act: -0.0000

Data Index: 1675890 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.4231. Min Act: -0.0000

Data Index: 1915623 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 4.0060. Min Range: -4.0060

Max Act: 3.1114. Min Act: -0.0000

Data Index: 519372 (The Pile)

Max Activating Token Index: 412