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

Dataset: The Pile

Neuron 2422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.3735. Min Act: -0.0000

Data Index: 791628 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.4235. Min Act: -0.0000

Data Index: 1096242 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.4637. Min Act: -0.0000

Data Index: 73338 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.9640. Min Act: -0.0000

Data Index: 1353976 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.7597. Min Act: -0.0000

Data Index: 1949581 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.0771. Min Act: -0.0000

Data Index: 2774 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.7633. Min Act: -0.0000

Data Index: 1379826 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.7656. Min Act: -0.0000

Data Index: 928142 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.8490. Min Act: -0.0000

Data Index: 1836539 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.8743. Min Act: -0.0000

Data Index: 1537991 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.2484. Min Act: -0.0000

Data Index: 587456 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.1465. Min Act: -0.0000

Data Index: 174887 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.2057. Min Act: -0.0000

Data Index: 242503 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.2186. Min Act: -0.0000

Data Index: 715221 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.9332. Min Act: -0.0000

Data Index: 1493761 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.3224. Min Act: -0.0000

Data Index: 686108 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.8916. Min Act: -0.0000

Data Index: 258171 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.0398. Min Act: -0.0000

Data Index: 1584581 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 3.4637. Min Range: -3.4637

Max Act: 2.1027. Min Act: -0.0000

Data Index: 292043 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 3.4637. Min Range: -3.4637

Max Act: 3.1247. Min Act: -0.0000

Data Index: 782507 (The Pile)

Max Activating Token Index: 792