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

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

Neuron 1288 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.1342. Min Act: -0.0000

Data Index: 532430 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.3186. Min Act: -0.0000

Data Index: 1016042 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.1806. Min Act: -0.0000

Data Index: 665688 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1285007 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.1965. Min Act: -0.0000

Data Index: 1132766 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 2.3186. Min Range: -2.3186

Max Act: 2.1852. Min Act: -0.0000

Data Index: 476707 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1293397 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1128535 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1174784 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.7427. Min Act: -0.0000

Data Index: 710576 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.8354. Min Act: -0.0000

Data Index: 653237 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.5524. Min Act: -0.0000

Data Index: 1124878 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.7337. Min Act: -0.0000

Data Index: 1051611 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.7351. Min Act: -0.0000

Data Index: 921630 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.6016. Min Act: -0.0000

Data Index: 475213 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.6967. Min Act: -0.0000

Data Index: 1297133 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.7068. Min Act: -0.0000

Data Index: 573290 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.6973. Min Act: -0.0000

Data Index: 431103 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.6859. Min Act: -0.0000

Data Index: 1254581 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 2.3186. Min Range: -2.3186

Max Act: 1.4440. Min Act: -0.0000

Data Index: 3882 (C4 (Web Text))

Max Activating Token Index: 695