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

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

Neuron 961 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3251. Min Act: -0.0001

Data Index: 1317093 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3030. Min Act: -0.0001

Data Index: 1332792 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1670. Min Act: -0.0001

Data Index: 156281 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0941. Min Act: -0.0001

Data Index: 845958 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1697. Min Act: -0.0001

Data Index: 523079 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0546. Min Act: -0.0001

Data Index: 722539 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9529. Min Act: -0.0001

Data Index: 622361 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.0297. Min Act: -0.0001

Data Index: 1052617 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9326. Min Act: -0.0001

Data Index: 724039 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9913. Min Act: -0.0001

Data Index: 911546 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9561. Min Act: -0.0001

Data Index: 437598 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8824. Min Act: -0.0001

Data Index: 375568 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8778. Min Act: -0.0001

Data Index: 618494 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9284. Min Act: -0.0001

Data Index: 662173 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9292. Min Act: -0.0001

Data Index: 706685 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9227. Min Act: -0.0001

Data Index: 872767 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9234. Min Act: -0.0001

Data Index: 1352511 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9112. Min Act: -0.0001

Data Index: 970270 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9639. Min Act: -0.0001

Data Index: 905890 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9000. Min Act: -0.0001

Data Index: 1037079 (C4 (Web Text))

Max Activating Token Index: 898