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

Dataset: The Pile

Neuron 358 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: 0.3771. Min Range: -0.3771

Max Act: 0.3719. Min Act: -0.0000

Data Index: 441764 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1797821 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.3226. Min Act: -0.0000

Data Index: 761984 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.3217. Min Act: -0.0000

Data Index: 142205 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1550436 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1955982 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1423568 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2799. Min Act: -0.0000

Data Index: 8256 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2092. Min Act: -0.0000

Data Index: 619214 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2451. Min Act: -0.0000

Data Index: 533389 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1975144 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1312329 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2548. Min Act: -0.0000

Data Index: 574846 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2059. Min Act: -0.0000

Data Index: 816217 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1137067 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2102. Min Act: -0.0000

Data Index: 106366 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2226. Min Act: -0.0000

Data Index: 414798 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1784. Min Act: -0.0000

Data Index: 954667 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2195. Min Act: -0.0000

Data Index: 663670 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1702340 (The Pile)

Max Activating Token Index: 114