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

Dataset: The Pile

Neuron 2644 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: 0.2582. Min Range: -0.2582

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1767423 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1839267 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1408919 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1280827 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2337. Min Act: -0.0000

Data Index: 264676 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1750786 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2335. Min Act: -0.0000

Data Index: 868302 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1638918 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1950284 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2255. Min Act: -0.0000

Data Index: 923923 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2201. Min Act: -0.0000

Data Index: 502524 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1663126 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1872909 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2311. Min Act: -0.0000

Data Index: 991561 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1502297 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2148. Min Act: -0.0000

Data Index: 593408 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2275. Min Act: 0.0000

Data Index: 605598 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2155. Min Act: -0.0000

Data Index: 836459 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2148. Min Act: -0.0000

Data Index: 247112 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.2582. Min Range: -0.2582

Max Act: 0.2154. Min Act: -0.0000

Data Index: 397162 (The Pile)

Max Activating Token Index: 930