Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1127 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.3169. Min Act: -0.0001

Data Index: 9765 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2939. Min Act: -0.0001

Data Index: 771017 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2835. Min Act: -0.0001

Data Index: 530903 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1147847 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2799. Min Act: -0.0001

Data Index: 894989 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2736. Min Act: -0.0001

Data Index: 53179 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2766. Min Act: -0.0001

Data Index: 213926 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1220621 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2385. Min Act: -0.0001

Data Index: 1029184 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2623. Min Act: -0.0001

Data Index: 361171 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2545. Min Act: -0.0001

Data Index: 207447 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2529. Min Act: -0.0001

Data Index: 411729 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1250729 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1166261 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2485. Min Act: -0.0001

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2578. Min Act: -0.0001

Data Index: 19108 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2391. Min Act: -0.0001

Data Index: 14483 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2463. Min Act: -0.0001

Data Index: 716673 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1213965 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2459. Min Act: -0.0001

Data Index: 908861 (C4 (Web Text))

Max Activating Token Index: 126