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

Dataset: The Pile

Neuron 2965 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: 5.4362. Min Range: -5.4362

Max Act: 5.4362. Min Act: -0.0000

Data Index: 1486185 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 5.4362. Min Range: -5.4362

Max Act: 3.4294. Min Act: -0.0000

Data Index: 1952727 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.9093. Min Act: -0.0001

Data Index: 1500113 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.9965. Min Act: -0.0000

Data Index: 636681 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 5.4362. Min Range: -5.4362

Max Act: 3.2410. Min Act: -0.0000

Data Index: 1067225 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.4574. Min Act: -0.0000

Data Index: 1813388 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.6344. Min Act: -0.0000

Data Index: 1160140 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.6593. Min Act: -0.0000

Data Index: 161186 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.3441. Min Act: -0.0000

Data Index: 1128778 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.5523. Min Act: -0.0000

Data Index: 1979799 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.4453. Min Act: -0.0000

Data Index: 664641 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.2899. Min Act: -0.0000

Data Index: 650855 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.4444. Min Act: -0.0000

Data Index: 1890577 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.4465. Min Act: -0.0000

Data Index: 41628 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.3958. Min Act: -0.0000

Data Index: 136596 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.4436. Min Act: -0.0000

Data Index: 736695 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.3514. Min Act: -0.0000

Data Index: 94906 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1000097 (The Pile)

Max Activating Token Index: 527

Text #18

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.2107. Min Act: -0.0000

Data Index: 1502232 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 5.4362. Min Range: -5.4362

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1779123 (The Pile)

Max Activating Token Index: 796