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

Dataset: The Pile

Neuron 5090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.4441. Min Act: -0.0000

Data Index: 117494 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1784561 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2711. Min Act: -0.0000

Data Index: 803584 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1537430 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3563. Min Act: -0.0000

Data Index: 921665 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1335. Min Act: -0.0000

Data Index: 996071 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1535. Min Act: -0.0000

Data Index: 437045 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0476. Min Act: -0.0000

Data Index: 210906 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1346887 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2235. Min Act: -0.0000

Data Index: 1946216 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1008765 (The Pile)

Max Activating Token Index: 234

Text #11

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0725. Min Act: -0.0000

Data Index: 229227 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0428. Min Act: -0.0000

Data Index: 521029 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2691. Min Act: -0.0000

Data Index: 557952 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1569924 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1809812 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1746126 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2230. Min Act: -0.0000

Data Index: 136564 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1777239 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1169760 (The Pile)

Max Activating Token Index: 248