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

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

Neuron 2513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6551. Min Range: -2.6551

Max Act: 2.6551. Min Act: -0.0000

Data Index: 548769 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.6551. Min Range: -2.6551

Max Act: 2.2444. Min Act: -0.0000

Data Index: 484178 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 2.6551. Min Range: -2.6551

Max Act: 2.2607. Min Act: -0.0000

Data Index: 946648 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.6551. Min Range: -2.6551

Max Act: 2.1132. Min Act: -0.0000

Data Index: 407914 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 2.6551. Min Range: -2.6551

Max Act: 2.0122. Min Act: -0.0000

Data Index: 128859 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.9785. Min Act: -0.0000

Data Index: 13142 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.9736. Min Act: -0.0000

Data Index: 339912 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.8717. Min Act: -0.0000

Data Index: 98235 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.9570. Min Act: -0.0000

Data Index: 518184 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.7726. Min Act: -0.0000

Data Index: 1216512 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1276507 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.6788. Min Act: -0.0000

Data Index: 917074 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1297173 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.6303. Min Act: -0.0000

Data Index: 136320 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.5837. Min Act: -0.0000

Data Index: 837278 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.6463. Min Act: -0.0000

Data Index: 421568 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1354350 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1324221 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.5955. Min Act: -0.0000

Data Index: 978093 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.6551. Min Range: -2.6551

Max Act: 1.5958. Min Act: -0.0000

Data Index: 620911 (C4 (Web Text))

Max Activating Token Index: 219