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

Dataset: The Pile

Neuron 929 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: 1.1929. Min Range: -1.1929

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1090737 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1808197 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1004040 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1493848 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9583. Min Act: -0.0000

Data Index: 3955 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 1.1929. Min Range: -1.1929

Max Act: 1.0420. Min Act: -0.0000

Data Index: 373281 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9324. Min Act: -0.0000

Data Index: 837498 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1305169 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9212. Min Act: -0.0000

Data Index: 90474 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9127. Min Act: -0.0000

Data Index: 696711 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1110361 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1780336 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1357532 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9364. Min Act: -0.0000

Data Index: 59143 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9226. Min Act: -0.0000

Data Index: 408741 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1148133 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8747. Min Act: -0.0000

Data Index: 489340 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1430995 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1129397 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 1.1929. Min Range: -1.1929

Max Act: 0.8214. Min Act: -0.0000

Data Index: 853928 (The Pile)

Max Activating Token Index: 174