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

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

Neuron 412 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: 0.3764. Min Range: -0.3764

Max Act: 0.3638. Min Act: -0.0000

Data Index: 330084 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3764. Min Act: -0.0001

Data Index: 854028 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1001659 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3318. Min Act: -0.0001

Data Index: 427630 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3342. Min Act: -0.0001

Data Index: 24448 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1192384 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3158. Min Act: -0.0001

Data Index: 757675 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3311. Min Act: -0.0001

Data Index: 1035927 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3111. Min Act: 0.0000

Data Index: 911791 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1141067 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2979. Min Act: -0.0000

Data Index: 885908 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2866. Min Act: 0.0000

Data Index: 1111253 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2968. Min Act: -0.0001

Data Index: 596144 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3042. Min Act: -0.0001

Data Index: 826510 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1278702 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2816. Min Act: -0.0001

Data Index: 915666 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2915. Min Act: -0.0001

Data Index: 914857 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2806. Min Act: -0.0001

Data Index: 875051 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2745. Min Act: -0.0001

Data Index: 200333 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2738. Min Act: -0.0001

Data Index: 731375 (C4 (Web Text))

Max Activating Token Index: 409