Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2551 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1127500 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1410. Min Act: -0.0000

Data Index: 433664 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1779163 (The Pile)

Max Activating Token Index: 851

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1872591 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1875481 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1212. Min Act: -0.0000

Data Index: 283850 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1206. Min Act: -0.0000

Data Index: 628766 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1237492 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1191. Min Act: -0.0000

Data Index: 486816 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1129. Min Act: -0.0000

Data Index: 316647 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1436974 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1440725 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1655476 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1816847 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1019053 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1143. Min Act: -0.0000

Data Index: 565509 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1059. Min Act: -0.0000

Data Index: 258144 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1237378 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1134. Min Act: -0.0000

Data Index: 626140 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1006416 (The Pile)

Max Activating Token Index: 276