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

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

Neuron 1854 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: 2.3442. Min Range: -2.3442

Max Act: 2.3442. Min Act: -0.0001

Data Index: 1146596 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.3322. Min Act: -0.0001

Data Index: 844162 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.1996. Min Act: -0.0001

Data Index: 818024 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.1843. Min Act: -0.0001

Data Index: 845011 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.1108. Min Act: -0.0001

Data Index: 262006 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.0791. Min Act: -0.0001

Data Index: 444430 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.0758. Min Act: -0.0001

Data Index: 1090728 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.9647. Min Act: -0.0001

Data Index: 206928 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.1598. Min Act: -0.0001

Data Index: 630233 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.8646. Min Act: -0.0001

Data Index: 1008870 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.8661. Min Act: -0.0001

Data Index: 738021 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.9600. Min Act: -0.0001

Data Index: 141479 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.8634. Min Act: -0.0001

Data Index: 431943 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.8593. Min Act: -0.0001

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.9654. Min Act: -0.0001

Data Index: 1079747 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.0546. Min Act: -0.0001

Data Index: 277034 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.8451. Min Act: -0.0001

Data Index: 22528 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 2.3442. Min Range: -2.3442

Max Act: 1.9550. Min Act: -0.0001

Data Index: 937240 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.0636. Min Act: -0.0001

Data Index: 716457 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.3442. Min Range: -2.3442

Max Act: 2.0415. Min Act: -0.0001

Data Index: 1126855 (C4 (Web Text))

Max Activating Token Index: 141