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

Dataset: The Pile

Neuron 4689 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.4715. Min Act: -0.0000

Data Index: 652049 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1845077 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1474463 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1072886 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1994146 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1707243 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 1.4715. Min Range: -1.4715

Max Act: 1.1145. Min Act: -0.0000

Data Index: 202359 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.9119. Min Act: 0.0000

Data Index: 1271677 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.9347. Min Act: -0.0000

Data Index: 272696 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.9060. Min Act: -0.0000

Data Index: 734300 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.8825. Min Act: -0.0000

Data Index: 890811 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.7607. Min Act: -0.0000

Data Index: 994634 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1202742 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1038251 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.7279. Min Act: -0.0000

Data Index: 872943 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.6616. Min Act: -0.0000

Data Index: 584423 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.6531. Min Act: -0.0000

Data Index: 713222 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1733458 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1490381 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 1.4715. Min Range: -1.4715

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1124664 (The Pile)

Max Activating Token Index: 474