Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4202. Min Range: -1.4202

Max Act: 1.4202. Min Act: -0.0000

Data Index: 301638 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1640253 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4478. Min Act: -0.0000

Data Index: 754024 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.6879. Min Act: -0.0000

Data Index: 401002 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.6866. Min Act: -0.0000

Data Index: 792412 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1430433 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.7054. Min Act: -0.0000

Data Index: 215117 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.5552. Min Act: -0.0000

Data Index: 868077 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4654. Min Act: -0.0000

Data Index: 673396 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3977. Min Act: -0.0000

Data Index: 386096 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4675. Min Act: -0.0000

Data Index: 642430 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4440. Min Act: -0.0000

Data Index: 192917 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1714066 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4127. Min Act: -0.0000

Data Index: 535770 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3953. Min Act: -0.0000

Data Index: 645464 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1084467 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1044364 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1938083 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3316. Min Act: -0.0000

Data Index: 698589 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1938640 (The Pile)

Max Activating Token Index: 876