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

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

Neuron 1293 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2312. Min Range: -1.2312

Max Act: 1.2312. Min Act: -0.0001

Data Index: 859583 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.2312. Min Range: -1.2312

Max Act: 1.2159. Min Act: -0.0001

Data Index: 473355 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.2312. Min Range: -1.2312

Max Act: 1.0892. Min Act: -0.0000

Data Index: 283544 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.2312. Min Range: -1.2312

Max Act: 1.0507. Min Act: -0.0001

Data Index: 848299 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9975. Min Act: -0.0001

Data Index: 1296048 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8736. Min Act: -0.0001

Data Index: 242341 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9676. Min Act: -0.0001

Data Index: 371221 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9400. Min Act: -0.0001

Data Index: 268052 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8592. Min Act: -0.0001

Data Index: 297186 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9041. Min Act: -0.0001

Data Index: 700149 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8689. Min Act: -0.0001

Data Index: 713313 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8966. Min Act: -0.0001

Data Index: 891019 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9200. Min Act: -0.0001

Data Index: 475681 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9154. Min Act: -0.0001

Data Index: 272895 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.9082. Min Act: -0.0001

Data Index: 161542 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8991. Min Act: -0.0001

Data Index: 470852 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8697. Min Act: -0.0001

Data Index: 862495 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8671. Min Act: -0.0001

Data Index: 92584 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.7999. Min Act: -0.0001

Data Index: 264574 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.2312. Min Range: -1.2312

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1027603 (C4 (Web Text))

Max Activating Token Index: 657