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

Dataset: The Pile

Neuron 164 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: 1.0645. Min Range: -1.0645

Max Act: 1.0645. Min Act: -0.0000

Data Index: 371970 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9639. Min Act: -0.0000

Data Index: 963061 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9084. Min Act: -0.0000

Data Index: 904589 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8553. Min Act: -0.0000

Data Index: 268290 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1910688 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7324. Min Act: -0.0000

Data Index: 699789 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1678045 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7815. Min Act: -0.0000

Data Index: 825030 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1859505 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1599697 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1506036 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1159904 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7799. Min Act: -0.0000

Data Index: 361786 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7614. Min Act: -0.0000

Data Index: 471108 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7486. Min Act: -0.0000

Data Index: 781569 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7038. Min Act: -0.0000

Data Index: 998171 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1191043 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7586. Min Act: -0.0000

Data Index: 922401 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1751732 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1273990 (The Pile)

Max Activating Token Index: 348