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

Dataset: The Pile

Neuron 1350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.5838. Min Act: -0.0000

Data Index: 426801 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.4714. Min Act: -0.0000

Data Index: 688823 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.6216. Min Act: -0.0000

Data Index: 1295888 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.4932. Min Act: -0.0000

Data Index: 1565796 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.6150. Min Act: -0.0000

Data Index: 397348 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.4667. Min Act: -0.0000

Data Index: 1274551 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.6235. Min Act: -0.0000

Data Index: 1256765 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.4174. Min Act: -0.0000

Data Index: 404517 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.4138. Min Act: -0.0000

Data Index: 1802155 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 5.6235. Min Range: -5.6235

Max Act: 4.4899. Min Act: -0.0000

Data Index: 1860625 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.3457. Min Act: -0.0000

Data Index: 1305732 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 5.6235. Min Range: -5.6235

Max Act: 4.9443. Min Act: -0.0000

Data Index: 1066383 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.3273. Min Act: -0.0000

Data Index: 332717 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.1057. Min Act: -0.0000

Data Index: 1116001 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.2728. Min Act: -0.0000

Data Index: 396146 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.0898. Min Act: -0.0000

Data Index: 335344 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.3526. Min Act: -0.0000

Data Index: 1255879 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.3193. Min Act: -0.0000

Data Index: 702836 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.1290. Min Act: -0.0000

Data Index: 1107167 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 5.6235. Min Range: -5.6235

Max Act: 5.1240. Min Act: -0.0000

Data Index: 1368568 (The Pile)

Max Activating Token Index: 422