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

Dataset: The Pile

Neuron 4459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5845. Min Act: -0.0000

Data Index: 656745 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4945. Min Act: -0.0000

Data Index: 332871 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4579. Min Act: -0.0000

Data Index: 883872 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5261. Min Act: -0.0000

Data Index: 296020 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1199213 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1407810 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1797961 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1986835 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1624077 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1352244 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1820302 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1768416 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3289. Min Act: -0.0000

Data Index: 686631 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1283058 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2935. Min Act: -0.0000

Data Index: 32521 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4629. Min Act: -0.0000

Data Index: 561473 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3534. Min Act: -0.0000

Data Index: 1259556 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1817661 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2968. Min Act: -0.0000

Data Index: 736235 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1323940 (The Pile)

Max Activating Token Index: 920