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

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

Neuron 4413 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7830. Min Act: -0.0000

Data Index: 100845 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7995. Min Act: -0.0000

Data Index: 757582 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1221883 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7328. Min Act: -0.0000

Data Index: 401109 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7513. Min Act: -0.0000

Data Index: 423696 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6965. Min Act: -0.0000

Data Index: 653482 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1060397 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1341163 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6593. Min Act: -0.0001

Data Index: 1193455 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5744. Min Act: -0.0000

Data Index: 276114 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6615. Min Act: -0.0000

Data Index: 752826 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6587. Min Act: -0.0000

Data Index: 381037 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1342319 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6137. Min Act: -0.0000

Data Index: 309986 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6276. Min Act: -0.0000

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6187. Min Act: -0.0000

Data Index: 679541 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6597. Min Act: -0.0000

Data Index: 370582 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6091. Min Act: -0.0000

Data Index: 221587 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1021104 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6271. Min Act: -0.0000

Data Index: 90101 (C4 (Web Text))

Max Activating Token Index: 142