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

Dataset: The Pile

Neuron 4806 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1503401 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1126927 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1361944 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1253873 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1841841 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1968951 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5845. Min Act: -0.0000

Data Index: 979248 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5965. Min Act: -0.0000

Data Index: 38980 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1444797 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1690812 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1995467 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1363686 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.4179. Min Act: -0.0000

Data Index: 912835 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1857840 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3511. Min Act: -0.0000

Data Index: 244036 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1952692 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3293. Min Act: -0.0000

Data Index: 905137 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3319. Min Act: -0.0000

Data Index: 184410 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3092. Min Act: -0.0000

Data Index: 94422 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.3093. Min Act: -0.0000

Data Index: 869362 (The Pile)

Max Activating Token Index: 837