Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1534896 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1385490 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1200903 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1324024 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3282. Min Act: -0.0000

Data Index: 497665 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1970420 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3304. Min Act: -0.0000

Data Index: 495212 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2867. Min Act: -0.0000

Data Index: 306121 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1214198 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1891390 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3081. Min Act: -0.0000

Data Index: 837261 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3262. Min Act: -0.0000

Data Index: 894460 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2875. Min Act: -0.0000

Data Index: 554832 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1296822 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1492957 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2797. Min Act: -0.0000

Data Index: 595076 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1896629 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1259950 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1646115 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1820038 (The Pile)

Max Activating Token Index: 371