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

Dataset: The Pile

Neuron 3442 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0433. Min Range: -3.0433

Max Act: 3.0433. Min Act: -0.0000

Data Index: 168369 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4528. Min Act: -0.0000

Data Index: 1600805 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.5101. Min Act: -0.0000

Data Index: 1254603 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2632. Min Act: -0.0000

Data Index: 180950 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4860. Min Act: -0.0000

Data Index: 1871994 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2389. Min Act: -0.0000

Data Index: 393304 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.1785. Min Act: -0.0000

Data Index: 1571318 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2524. Min Act: -0.0000

Data Index: 344287 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4092. Min Act: -0.0000

Data Index: 53070 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.7249. Min Act: -0.0000

Data Index: 748596 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.8522. Min Act: -0.0000

Data Index: 164735 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.8429. Min Act: -0.0000

Data Index: 812123 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1705138 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.8352. Min Act: -0.0000

Data Index: 193167 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.8415. Min Act: -0.0000

Data Index: 1300999 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1206222 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.8515. Min Act: -0.0000

Data Index: 1877016 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.5980. Min Act: -0.0000

Data Index: 74166 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.7641. Min Act: -0.0000

Data Index: 1568534 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 3.0433. Min Range: -3.0433

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1207306 (The Pile)

Max Activating Token Index: 565