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

Dataset: The Pile

Neuron 1408 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: 3.7550. Min Range: -3.7550

Max Act: 3.7550. Min Act: -0.0000

Data Index: 1735849 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.7412. Min Act: -0.0000

Data Index: 1504035 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.7449. Min Act: -0.0000

Data Index: 1574713 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.5649. Min Act: -0.0000

Data Index: 243844 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6569. Min Act: -0.0000

Data Index: 277727 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.4558. Min Act: -0.0000

Data Index: 334195 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.4944. Min Act: -0.0000

Data Index: 152253 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.1867. Min Act: -0.0000

Data Index: 197280 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6269. Min Act: -0.0000

Data Index: 1744993 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.1655. Min Act: -0.0000

Data Index: 1861179 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.3373. Min Act: -0.0000

Data Index: 404335 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.1219. Min Act: -0.0000

Data Index: 1737145 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.3691. Min Act: -0.0000

Data Index: 1296156 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.3853. Min Act: -0.0000

Data Index: 938388 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6877. Min Act: -0.0000

Data Index: 1539075 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.2034. Min Act: -0.0000

Data Index: 227084 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.0587. Min Act: -0.0000

Data Index: 1421403 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.2014. Min Act: -0.0000

Data Index: 1881838 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.4869. Min Act: -0.0000

Data Index: 57284 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.2117. Min Act: -0.0000

Data Index: 1353596 (The Pile)

Max Activating Token Index: 735