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

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

Neuron 4198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.6782. Min Act: -0.0001

Data Index: 47106 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1328325 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1190028 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5524. Min Act: -0.0001

Data Index: 753951 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5708. Min Act: -0.0001

Data Index: 231524 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5954. Min Act: -0.0001

Data Index: 736281 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5051. Min Act: -0.0001

Data Index: 1329978 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.5165. Min Act: -0.0001

Data Index: 839168 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4965. Min Act: -0.0001

Data Index: 665019 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4796. Min Act: -0.0001

Data Index: 811464 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4387. Min Act: -0.0001

Data Index: 1263180 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1055345 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4820. Min Act: -0.0001

Data Index: 742791 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4744. Min Act: -0.0001

Data Index: 1326725 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4678. Min Act: -0.0001

Data Index: 958121 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4601. Min Act: -0.0001

Data Index: 377804 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4821. Min Act: -0.0001

Data Index: 954291 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4780. Min Act: -0.0001

Data Index: 284419 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4196. Min Act: -0.0001

Data Index: 635041 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.4742. Min Act: -0.0001

Data Index: 755984 (C4 (Web Text))

Max Activating Token Index: 395