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

Dataset: The Pile

Neuron 4203 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: 0.7797. Min Range: -0.7797

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1303546 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7136. Min Act: -0.0000

Data Index: 735625 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6728. Min Act: -0.0000

Data Index: 482739 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6942. Min Act: -0.0000

Data Index: 256595 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7114. Min Act: -0.0000

Data Index: 774702 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1331055 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6456. Min Act: -0.0000

Data Index: 71168 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7044. Min Act: -0.0000

Data Index: 348462 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1492989 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1770659 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6131. Min Act: -0.0000

Data Index: 114441 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6220. Min Act: -0.0000

Data Index: 703199 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1290023 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1417106 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1160237 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1255942 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6124. Min Act: -0.0000

Data Index: 975011 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1236128 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5856. Min Act: -0.0000

Data Index: 716950 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6267. Min Act: -0.0000

Data Index: 824187 (The Pile)

Max Activating Token Index: 32