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

Dataset: The Pile

Neuron 3205 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: 1.7346. Min Range: -1.7346

Max Act: 1.7346. Min Act: -0.0000

Data Index: 1296783 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4188. Min Act: -0.0000

Data Index: 401025 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1070744 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1279042 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1325461 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1824718 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.4121. Min Act: -0.0000

Data Index: 938885 (The Pile)

Max Activating Token Index: 14

Text #7

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1963556 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3525. Min Act: -0.0000

Data Index: 661687 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2963. Min Act: -0.0000

Data Index: 755372 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1708399 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1493530 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1034251 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1108297 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2719. Min Act: -0.0000

Data Index: 219198 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1323519 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2541. Min Act: -0.0000

Data Index: 720516 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.3199. Min Act: -0.0000

Data Index: 44688 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2425. Min Act: -0.0000

Data Index: 831587 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.7346. Min Range: -1.7346

Max Act: 1.2459. Min Act: -0.0000

Data Index: 993925 (The Pile)

Max Activating Token Index: 57