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

Dataset: The Pile

Neuron 3775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0000

Data Index: 334289 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2607. Min Act: -0.0000

Data Index: 218250 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1309470 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1469108 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1994491 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2109. Min Act: -0.0000

Data Index: 257875 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1456473 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1851191 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1414263 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1499200 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2197. Min Act: -0.0000

Data Index: 941374 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1256277 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2354. Min Act: -0.0000

Data Index: 631968 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1363775 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1308203 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1284245 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2269. Min Act: -0.0000

Data Index: 624075 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1700298 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2262. Min Act: -0.0000

Data Index: 437105 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1962. Min Act: -0.0000

Data Index: 454871 (The Pile)

Max Activating Token Index: 122