Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.4666. Min Act: -0.0000

Data Index: 183549 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1070. Min Act: -0.0001

Data Index: 878769 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.0925. Min Act: -0.0001

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.8978. Min Act: -0.0001

Data Index: 758780 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.8508. Min Act: -0.0001

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.8681. Min Act: -0.0000

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.8215. Min Act: -0.0001

Data Index: 975773 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.7001. Min Act: -0.0000

Data Index: 570610 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.7211. Min Act: -0.0001

Data Index: 1143212 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.7222. Min Act: -0.0001

Data Index: 1257701 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.7056. Min Act: -0.0000

Data Index: 6645 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1198998 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.4898. Min Act: -0.0001

Data Index: 841127 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.6166. Min Act: -0.0001

Data Index: 1138250 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.5882. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.5443. Min Act: -0.0001

Data Index: 443752 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.6011. Min Act: -0.0000

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.5425. Min Act: -0.0001

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.4666. Min Range: -1.4666

Max Act: 0.5828. Min Act: -0.0001

Data Index: 193716 (C4 (Web Text))

Max Activating Token Index: 639