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

Dataset: The Pile

Neuron 867 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: 0.4689. Min Range: -0.4689

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1574932 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.4340. Min Act: -0.0000

Data Index: 776273 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1538334 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3538. Min Act: -0.0000

Data Index: 145005 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1811270 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3399. Min Act: -0.0000

Data Index: 259870 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1566819 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1201612 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3294. Min Act: -0.0000

Data Index: 306264 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2907. Min Act: -0.0000

Data Index: 130913 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1173088 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3345. Min Act: -0.0000

Data Index: 86464 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2990. Min Act: -0.0000

Data Index: 779390 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1939800 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1798605 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1568066 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1394140 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2919. Min Act: -0.0000

Data Index: 696351 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1035567 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.4689. Min Range: -0.4689

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1836931 (The Pile)

Max Activating Token Index: 291