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

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

Neuron 4516 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: 1.8353. Min Range: -1.8353

Max Act: 1.6057. Min Act: -0.0001

Data Index: 392494 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.6136. Min Act: -0.0001

Data Index: 600717 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.6264. Min Act: -0.0001

Data Index: 1137548 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.5136. Min Act: -0.0001

Data Index: 920143 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.4972. Min Act: -0.0001

Data Index: 1002292 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.4834. Min Act: -0.0001

Data Index: 991960 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.4697. Min Act: -0.0001

Data Index: 95772 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.4328. Min Act: -0.0001

Data Index: 882723 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3400. Min Act: -0.0001

Data Index: 935246 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3423. Min Act: -0.0001

Data Index: 75606 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.8353. Min Act: -0.0001

Data Index: 356510 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3278. Min Act: -0.0001

Data Index: 1220400 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3070. Min Act: -0.0001

Data Index: 488966 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.2502. Min Act: -0.0001

Data Index: 259177 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3677. Min Act: -0.0001

Data Index: 373761 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.2596. Min Act: -0.0001

Data Index: 611334 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.2041. Min Act: -0.0001

Data Index: 830654 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1237417 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.3258. Min Act: -0.0001

Data Index: 222466 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.8353. Min Range: -1.8353

Max Act: 1.2852. Min Act: -0.0001

Data Index: 745379 (C4 (Web Text))

Max Activating Token Index: 390