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

Dataset: The Pile

Neuron 4068 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: 1.3699. Min Range: -1.3699

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1861189 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.3629. Min Act: -0.0000

Data Index: 1626833 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.3699. Min Act: -0.0000

Data Index: 261686 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.3586. Min Act: -0.0000

Data Index: 995593 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.2487. Min Act: -0.0000

Data Index: 427983 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1771. Min Act: -0.0000

Data Index: 835609 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.2688. Min Act: -0.0000

Data Index: 375949 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1408257 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1414. Min Act: -0.0000

Data Index: 125658 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1550314 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1015335 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1452. Min Act: -0.0000

Data Index: 310813 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1684. Min Act: -0.0000

Data Index: 566108 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1015072 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1722104 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.3086. Min Act: -0.0000

Data Index: 970750 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.1121. Min Act: -0.0000

Data Index: 489089 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0343. Min Act: -0.0000

Data Index: 311299 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1861533 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0443. Min Act: -0.0000

Data Index: 217700 (The Pile)

Max Activating Token Index: 121