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

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

Neuron 5041 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.6179. Min Act: -0.0000

Data Index: 486216 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1095031 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4208. Min Act: -0.0000

Data Index: 662292 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4412. Min Act: -0.0000

Data Index: 337774 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4059. Min Act: -0.0000

Data Index: 965906 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4416. Min Act: -0.0000

Data Index: 8218 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4508. Min Act: -0.0000

Data Index: 37939 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3973. Min Act: -0.0000

Data Index: 945197 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4011. Min Act: -0.0000

Data Index: 499986 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4144. Min Act: -0.0000

Data Index: 878098 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1210468 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1042697 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1207131 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1026323 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3619. Min Act: -0.0000

Data Index: 797757 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3695. Min Act: -0.0000

Data Index: 222753 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3608. Min Act: -0.0000

Data Index: 518292 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1206635 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3362. Min Act: -0.0000

Data Index: 319203 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1151745 (C4 (Web Text))

Max Activating Token Index: 500