Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.6094. Min Act: -0.0001

Data Index: 1051828 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.5649. Min Act: -0.0000

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1435670 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1562390 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.4178. Min Act: -0.0001

Data Index: 1071568 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.4017. Min Act: -0.0000

Data Index: 953770 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3419. Min Act: -0.0001

Data Index: 763488 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3401. Min Act: -0.0000

Data Index: 45097 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2670. Min Act: -0.0001

Data Index: 601241 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1367200 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3437. Min Act: -0.0001

Data Index: 759261 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3411. Min Act: -0.0001

Data Index: 567818 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2268. Min Act: -0.0001

Data Index: 93721 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3136. Min Act: -0.0001

Data Index: 806782 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2756. Min Act: -0.0001

Data Index: 1226294 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.3936. Min Act: -0.0001

Data Index: 1262549 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2622. Min Act: -0.0001

Data Index: 658651 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2979. Min Act: -0.0001

Data Index: 746575 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1344894 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.6094. Min Range: -1.6094

Max Act: 1.2107. Min Act: -0.0001

Data Index: 1055747 (C4 (Web Text))

Max Activating Token Index: 920