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

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

Neuron 4226 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.7499. Min Act: -0.0000

Data Index: 888126 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.6974. Min Act: -0.0000

Data Index: 1104367 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.6944. Min Act: -0.0000

Data Index: 1237589 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.7823. Min Act: -0.0000

Data Index: 138159 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.6595. Min Act: -0.0000

Data Index: 210770 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.7480. Min Act: -0.0000

Data Index: 509783 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1032521 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.6453. Min Act: -0.0000

Data Index: 1346672 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1026230 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.4876. Min Act: -0.0000

Data Index: 953562 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.3760. Min Act: -0.0000

Data Index: 802106 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.3716. Min Act: -0.0000

Data Index: 560847 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.4492. Min Act: -0.0000

Data Index: 856382 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.5956. Min Act: -0.0000

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.5018. Min Act: -0.0000

Data Index: 201460 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.4698. Min Act: -0.0000

Data Index: 525032 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.3683. Min Act: -0.0000

Data Index: 417847 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.3606. Min Act: -0.0000

Data Index: 796775 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.2539. Min Act: -0.0000

Data Index: 428769 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.7823. Min Range: -1.7823

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1286157 (C4 (Web Text))

Max Activating Token Index: 229