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

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

Neuron 2072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5450. Min Act: -0.0000

Data Index: 551579 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5478. Min Act: -0.0000

Data Index: 554645 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4846. Min Act: -0.0000

Data Index: 482113 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4678. Min Act: -0.0000

Data Index: 890178 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5164. Min Act: -0.0000

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4713. Min Act: -0.0000

Data Index: 548882 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5146. Min Act: -0.0000

Data Index: 885018 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4575. Min Act: -0.0000

Data Index: 284851 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1177210 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1191431 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4285. Min Act: -0.0000

Data Index: 9398 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5054. Min Act: -0.0000

Data Index: 335337 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4586. Min Act: -0.0000

Data Index: 821132 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4643. Min Act: -0.0000

Data Index: 182933 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4702. Min Act: -0.0000

Data Index: 602203 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4774. Min Act: -0.0000

Data Index: 592454 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1234866 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4840. Min Act: -0.0000

Data Index: 67301 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4787. Min Act: -0.0000

Data Index: 693164 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1155680 (C4 (Web Text))

Max Activating Token Index: 660