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

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

Neuron 1145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1428415 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.8973. Min Act: -0.0001

Data Index: 413720 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.8819. Min Act: -0.0001

Data Index: 1620980 (Python Code)

Max Activating Token Index: 201

Text #3

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1371261 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1561099 (Python Code)

Max Activating Token Index: 271

Text #5

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.7611. Min Act: -0.0001

Data Index: 636666 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.6914. Min Act: -0.0001

Data Index: 1085838 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.6047. Min Act: -0.0001

Data Index: 787300 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1311658 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5494. Min Act: -0.0001

Data Index: 1186041 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5242. Min Act: -0.0001

Data Index: 1159146 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5705. Min Act: -0.0001

Data Index: 508637 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1048892 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5004. Min Act: -0.0001

Data Index: 1258028 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5463. Min Act: -0.0001

Data Index: 835779 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1285866 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.4793. Min Act: -0.0001

Data Index: 10110 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.4922. Min Act: -0.0001

Data Index: 1219275 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.4860. Min Act: -0.0001

Data Index: 905230 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.9470. Min Range: -0.9470

Max Act: 0.4591. Min Act: -0.0001

Data Index: 863115 (C4 (Web Text))

Max Activating Token Index: 733