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

Dataset: The Pile

Neuron 2581 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: 3.0083. Min Range: -3.0083

Max Act: 3.0083. Min Act: -0.0000

Data Index: 1268303 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.9598. Min Act: -0.0000

Data Index: 212900 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.7561. Min Act: -0.0000

Data Index: 167466 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.5938. Min Act: -0.0000

Data Index: 317308 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.5480. Min Act: -0.0000

Data Index: 52853 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.3892. Min Act: -0.0000

Data Index: 1291923 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.4383. Min Act: -0.0000

Data Index: 144749 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.5472. Min Act: -0.0000

Data Index: 35416 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.3464. Min Act: -0.0000

Data Index: 1932154 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.3359. Min Act: -0.0000

Data Index: 1602509 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.2608. Min Act: -0.0000

Data Index: 1147999 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.3551. Min Act: -0.0000

Data Index: 1998518 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0378. Min Act: -0.0000

Data Index: 66488 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.1753. Min Act: -0.0000

Data Index: 802409 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0159. Min Act: -0.0000

Data Index: 1886184 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0135. Min Act: -0.0000

Data Index: 1683405 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.2128. Min Act: -0.0000

Data Index: 126481 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0872. Min Act: -0.0000

Data Index: 88908 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0939. Min Act: -0.0000

Data Index: 684146 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 3.0083. Min Range: -3.0083

Max Act: 2.0628. Min Act: -0.0000

Data Index: 242512 (The Pile)

Max Activating Token Index: 1004