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

Dataset: The Pile

Neuron 162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5964. Min Act: 0.0000

Data Index: 11661 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5398. Min Act: -0.0000

Data Index: 633684 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1231740 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4860. Min Act: -0.0000

Data Index: 237668 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4978. Min Act: -0.0000

Data Index: 70925 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1726870 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4913. Min Act: -0.0000

Data Index: 348269 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1669806 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1569224 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4551. Min Act: -0.0000

Data Index: 872014 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4240. Min Act: -0.0000

Data Index: 232490 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4200. Min Act: -0.0000

Data Index: 470584 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4658. Min Act: -0.0000

Data Index: 566216 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4605. Min Act: -0.0000

Data Index: 651935 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1587770 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1641325 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1922871 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1174118 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4414. Min Act: -0.0000

Data Index: 639845 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1941976 (The Pile)

Max Activating Token Index: 307