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

Dataset: The Pile

Neuron 4675 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: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1547135 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1327818 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7071. Min Act: -0.0000

Data Index: 891119 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1362169 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1160688 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6604. Min Act: -0.0000

Data Index: 773943 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1187705 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1316703 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1014333 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6406. Min Act: -0.0000

Data Index: 87083 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6459. Min Act: -0.0000

Data Index: 146663 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1289179 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1712025 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5187. Min Act: -0.0000

Data Index: 875424 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1845573 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5977. Min Act: -0.0000

Data Index: 350733 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5877. Min Act: -0.0000

Data Index: 807661 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5998. Min Act: -0.0000

Data Index: 418619 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5636. Min Act: -0.0000

Data Index: 53158 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5468. Min Act: -0.0000

Data Index: 115985 (The Pile)

Max Activating Token Index: 424