Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.4295. Min Act: -0.0001

Data Index: 102133 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1057223 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3323. Min Act: -0.0001

Data Index: 934321 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2968. Min Act: -0.0001

Data Index: 94451 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2976. Min Act: -0.0001

Data Index: 853833 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3269. Min Act: -0.0001

Data Index: 481093 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2709. Min Act: -0.0001

Data Index: 664953 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2794. Min Act: -0.0001

Data Index: 1234041 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2656. Min Act: -0.0001

Data Index: 280275 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2741. Min Act: -0.0001

Data Index: 230974 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2712. Min Act: -0.0001

Data Index: 728692 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2661. Min Act: -0.0001

Data Index: 557250 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2312. Min Act: -0.0001

Data Index: 74681 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2697. Min Act: -0.0001

Data Index: 1317302 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2521. Min Act: -0.0001

Data Index: 523360 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2731. Min Act: -0.0001

Data Index: 308439 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2647. Min Act: -0.0001

Data Index: 683222 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1153257 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1118774 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.2517. Min Act: -0.0000

Data Index: 596380 (C4 (Web Text))

Max Activating Token Index: 555