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

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

Neuron 2202 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1284245 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6239. Min Act: -0.0001

Data Index: 718699 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6619. Min Act: -0.0001

Data Index: 470589 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6353. Min Act: -0.0001

Data Index: 809672 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5993. Min Act: -0.0001

Data Index: 268211 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5316. Min Act: -0.0001

Data Index: 453096 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5417. Min Act: -0.0001

Data Index: 88602 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5601. Min Act: -0.0001

Data Index: 491206 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.6282. Min Act: -0.0001

Data Index: 378490 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5773. Min Act: -0.0001

Data Index: 340166 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1137095 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5693. Min Act: -0.0001

Data Index: 259787 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5306. Min Act: -0.0001

Data Index: 14018 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5667. Min Act: -0.0001

Data Index: 844201 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.4633. Min Act: -0.0001

Data Index: 1207254 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5579. Min Act: -0.0001

Data Index: 1204156 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1063947 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5596. Min Act: -0.0001

Data Index: 1307213 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5203. Min Act: -0.0001

Data Index: 251084 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.6619. Min Range: -0.6619

Max Act: 0.5004. Min Act: -0.0001

Data Index: 101825 (C4 (Web Text))

Max Activating Token Index: 489