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

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

Neuron 1438 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: 1.1994. Min Range: -1.1994

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1239674 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.7682. Min Act: -0.0000

Data Index: 552226 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6803. Min Act: -0.0000

Data Index: 567420 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5917. Min Act: -0.0000

Data Index: 664822 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5862. Min Act: -0.0000

Data Index: 914589 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5643. Min Act: -0.0000

Data Index: 216647 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5415. Min Act: -0.0000

Data Index: 64859 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5190. Min Act: -0.0000

Data Index: 670882 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1071419 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4813. Min Act: -0.0000

Data Index: 145925 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4560. Min Act: -0.0000

Data Index: 278235 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1022660 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4211. Min Act: -0.0000

Data Index: 667831 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1249093 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4481. Min Act: 0.0000

Data Index: 990060 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4197. Min Act: -0.0000

Data Index: 471678 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4082. Min Act: 0.0000

Data Index: 383922 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1111643 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4197. Min Act: -0.0000

Data Index: 264420 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.4081. Min Act: -0.0000

Data Index: 204676 (C4 (Web Text))

Max Activating Token Index: 576