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

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

Neuron 373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.3530. Min Act: -0.0000

Data Index: 1240581 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.5045. Min Act: -0.0000

Data Index: 22053 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.2121. Min Act: -0.0000

Data Index: 203567 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.0950. Min Act: -0.0000

Data Index: 341032 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.0420. Min Act: -0.0000

Data Index: 111234 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 4.5045. Min Range: -4.5045

Max Act: 4.0168. Min Act: -0.0000

Data Index: 1336704 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.9613. Min Act: -0.0000

Data Index: 173749 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.5492. Min Act: -0.0000

Data Index: 1119954 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8525. Min Act: -0.0000

Data Index: 1147147 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8541. Min Act: -0.0000

Data Index: 55944 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8523. Min Act: -0.0000

Data Index: 462802 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8432. Min Act: -0.0000

Data Index: 219883 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.9535. Min Act: -0.0000

Data Index: 395082 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.7890. Min Act: -0.0000

Data Index: 1151031 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.6274. Min Act: -0.0000

Data Index: 687277 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.7953. Min Act: -0.0000

Data Index: 592720 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8968. Min Act: -0.0000

Data Index: 3809 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.5430. Min Act: -0.0000

Data Index: 827006 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.8912. Min Act: -0.0000

Data Index: 439625 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 4.5045. Min Range: -4.5045

Max Act: 3.7091. Min Act: -0.0000

Data Index: 45657 (C4 (Web Text))

Max Activating Token Index: 933