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

Dataset: The Pile

Neuron 692 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: 1.6489. Min Range: -1.6489

Max Act: 1.6489. Min Act: -0.0000

Data Index: 1464449 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.5731. Min Act: 0.0000

Data Index: 1506347 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4611. Min Act: -0.0000

Data Index: 619006 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3657. Min Act: -0.0000

Data Index: 522882 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1972142 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1275491 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1629580 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1249788 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2318. Min Act: -0.0000

Data Index: 577137 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1169585 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1047432 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1573291 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2149. Min Act: -0.0000

Data Index: 691373 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1060486 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1184623 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3083. Min Act: -0.0000

Data Index: 431420 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3018. Min Act: -0.0000

Data Index: 742371 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1426821 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.3721. Min Act: -0.0000

Data Index: 669946 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 1.6489. Min Range: -1.6489

Max Act: 1.2084. Min Act: -0.0000

Data Index: 238314 (The Pile)

Max Activating Token Index: 122