Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.3478. Min Act: -0.0000

Data Index: 135792 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.4426. Min Act: -0.0000

Data Index: 51511 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.4925. Min Act: -0.0000

Data Index: 143784 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.3275. Min Act: -0.0000

Data Index: 185969 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.4092. Min Act: -0.0000

Data Index: 686792 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.2724. Min Act: -0.0000

Data Index: 1358951 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.2887. Min Act: -0.0000

Data Index: 423089 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.1064. Min Act: -0.0000

Data Index: 320341 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.1144. Min Act: -0.0000

Data Index: 731598 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.2232. Min Act: -0.0000

Data Index: 1089390 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.0938. Min Act: -0.0000

Data Index: 1221330 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1229394 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.0763. Min Act: -0.0000

Data Index: 830630 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.0421. Min Act: -0.0000

Data Index: 1328456 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.0481. Min Act: -0.0000

Data Index: 893537 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.0490. Min Act: -0.0000

Data Index: 607694 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 2.4925. Min Range: -2.4925

Max Act: 1.9095. Min Act: -0.0000

Data Index: 1261868 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.1249. Min Act: -0.0000

Data Index: 759679 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.1021. Min Act: -0.0000

Data Index: 541871 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 2.4925. Min Range: -2.4925

Max Act: 2.1017. Min Act: -0.0000

Data Index: 372395 (C4 (Web Text))

Max Activating Token Index: 1019