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

Dataset: The Pile

Neuron 1203 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: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1625650 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1817717 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2448. Min Act: -0.0000

Data Index: 976286 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1493385 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1657224 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1942. Min Act: -0.0000

Data Index: 937328 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1941012 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2086. Min Act: -0.0000

Data Index: 67428 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1995. Min Act: -0.0000

Data Index: 441672 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1912981 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1986186 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1826. Min Act: -0.0000

Data Index: 390745 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1561759 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1251884 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1801412 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1919919 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1756. Min Act: -0.0000

Data Index: 522894 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1093089 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1765. Min Act: -0.0000

Data Index: 683957 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1250965 (The Pile)

Max Activating Token Index: 449