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

Dataset: The Pile

Neuron 3303 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: 0.5471. Min Range: -0.5471

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1867128 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1116723 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5238. Min Act: -0.0000

Data Index: 269628 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5177. Min Act: -0.0000

Data Index: 58667 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5271. Min Act: -0.0000

Data Index: 952629 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1904546 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1305623 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4995. Min Act: -0.0000

Data Index: 246370 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1183649 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1942662 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4859. Min Act: -0.0000

Data Index: 682363 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1678111 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4676. Min Act: -0.0000

Data Index: 972437 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3997. Min Act: -0.0000

Data Index: 994210 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4266. Min Act: -0.0000

Data Index: 130001 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4420. Min Act: -0.0000

Data Index: 933713 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1159082 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4264. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4319. Min Act: -0.0000

Data Index: 13015 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3970. Min Act: -0.0000

Data Index: 281028 (The Pile)

Max Activating Token Index: 142