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

Dataset: The Pile

Neuron 2767 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.4485. Min Act: -0.0000

Data Index: 7738 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1863448 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.2961. Min Act: -0.0000

Data Index: 717741 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1906. Min Act: -0.0000

Data Index: 714243 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1381031 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1752128 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1758888 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1991. Min Act: -0.0000

Data Index: 723351 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1412506 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1591935 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1064. Min Act: -0.0000

Data Index: 603653 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1699. Min Act: -0.0000

Data Index: 693564 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0180. Min Act: -0.0000

Data Index: 812223 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1879705 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1156782 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9627. Min Act: -0.0000

Data Index: 719777 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1684215 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 1.4485. Min Range: -1.4485

Max Act: 0.9013. Min Act: -0.0000

Data Index: 774688 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.0192. Min Act: -0.0000

Data Index: 943983 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.4485. Min Range: -1.4485

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1314077 (The Pile)

Max Activating Token Index: 663