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

Dataset: The Pile

Neuron 1582 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: 0.4711. Min Range: -0.4711

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1264299 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4606. Min Act: -0.0000

Data Index: 286656 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4301. Min Act: -0.0000

Data Index: 441916 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1370662 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4460. Min Act: -0.0000

Data Index: 738528 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1074849 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1790674 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4132. Min Act: -0.0000

Data Index: 295380 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1720070 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1101329 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1279488 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4039. Min Act: -0.0000

Data Index: 427259 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1327069 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3916. Min Act: -0.0000

Data Index: 543673 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4022. Min Act: -0.0000

Data Index: 45728 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1183524 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1305463 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3716. Min Act: -0.0000

Data Index: 698283 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1025763 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4003. Min Act: -0.0000

Data Index: 465329 (The Pile)

Max Activating Token Index: 694