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

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

Neuron 252 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: 0.8017. Min Range: -0.8017

Max Act: 0.8017. Min Act: -0.0001

Data Index: 806662 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7388. Min Act: -0.0001

Data Index: 12104 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6830. Min Act: -0.0001

Data Index: 804145 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6966. Min Act: -0.0001

Data Index: 288730 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6560. Min Act: -0.0001

Data Index: 175426 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6495. Min Act: -0.0001

Data Index: 484983 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6346. Min Act: -0.0001

Data Index: 688831 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5521. Min Act: -0.0001

Data Index: 688838 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5380. Min Act: -0.0001

Data Index: 235441 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6187. Min Act: -0.0001

Data Index: 106119 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1151023 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5391. Min Act: -0.0001

Data Index: 474768 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1063747 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5165. Min Act: -0.0001

Data Index: 238992 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5445. Min Act: -0.0001

Data Index: 1274179 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5479. Min Act: -0.0001

Data Index: 210698 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1131374 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5068. Min Act: -0.0001

Data Index: 245454 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1359838 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5080. Min Act: -0.0001

Data Index: 254248 (C4 (Web Text))

Max Activating Token Index: 902