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

Dataset: The Pile

Neuron 1263 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.9070. Min Act: -0.0000

Data Index: 379164 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1038692 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8659. Min Act: -0.0000

Data Index: 365830 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8567. Min Act: -0.0000

Data Index: 193133 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1200873 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1442739 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1234916 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1321856 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1226202 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1611341 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8059. Min Act: 0.0000

Data Index: 51713 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7832. Min Act: -0.0000

Data Index: 576403 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7697. Min Act: -0.0000

Data Index: 166770 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7672. Min Act: -0.0000

Data Index: 660157 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1614700 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7973. Min Act: -0.0000

Data Index: 849096 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7434. Min Act: -0.0000

Data Index: 656458 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1128963 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7619. Min Act: -0.0000

Data Index: 599518 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1567938 (The Pile)

Max Activating Token Index: 830