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

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

Neuron 3749 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: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0000

Data Index: 331394 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4882. Min Act: -0.0000

Data Index: 599501 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4458. Min Act: -0.0000

Data Index: 874774 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4625. Min Act: -0.0000

Data Index: 31285 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4420. Min Act: -0.0000

Data Index: 809528 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4333. Min Act: -0.0000

Data Index: 562531 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4188. Min Act: -0.0000

Data Index: 245019 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4164. Min Act: -0.0000

Data Index: 566525 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4175. Min Act: -0.0000

Data Index: 329785 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4168. Min Act: -0.0000

Data Index: 864457 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3909. Min Act: -0.0000

Data Index: 970848 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1354470 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3976. Min Act: -0.0000

Data Index: 141009 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3838. Min Act: -0.0000

Data Index: 845741 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3946. Min Act: -0.0000

Data Index: 289233 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4061. Min Act: -0.0000

Data Index: 620905 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1194568 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1265834 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1306139 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3752. Min Act: -0.0000

Data Index: 427613 (C4 (Web Text))

Max Activating Token Index: 996