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

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

Neuron 588 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0000

Data Index: 208646 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8645. Min Act: -0.0000

Data Index: 657262 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8120. Min Act: -0.0000

Data Index: 276467 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9082. Min Act: -0.0000

Data Index: 722119 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7752. Min Act: -0.0000

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7731. Min Act: -0.0000

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1240503 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6353. Min Act: -0.0000

Data Index: 432611 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6746. Min Act: -0.0000

Data Index: 309315 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6715. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6683. Min Act: -0.0000

Data Index: 483986 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1266733 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6185. Min Act: -0.0000

Data Index: 847490 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6567. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6107. Min Act: -0.0000

Data Index: 660557 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5747. Min Act: -0.0000

Data Index: 431296 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1170981 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5777. Min Act: -0.0000

Data Index: 840486 (C4 (Web Text))

Max Activating Token Index: 163