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

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

Neuron 3422 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: 1.5510. Min Range: -1.5510

Max Act: 1.5510. Min Act: -0.0001

Data Index: 865629 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5093. Min Act: -0.0001

Data Index: 1211971 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3537. Min Act: -0.0001

Data Index: 337954 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3779. Min Act: -0.0001

Data Index: 234772 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3411. Min Act: -0.0001

Data Index: 1286422 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3040. Min Act: -0.0001

Data Index: 42179 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2927. Min Act: -0.0001

Data Index: 877790 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2703. Min Act: -0.0001

Data Index: 329012 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2268. Min Act: -0.0001

Data Index: 227515 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1785. Min Act: -0.0001

Data Index: 532369 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2498. Min Act: -0.0001

Data Index: 511494 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3014. Min Act: -0.0001

Data Index: 964428 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1357467 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1915. Min Act: -0.0001

Data Index: 1146417 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2331. Min Act: -0.0001

Data Index: 740784 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2192. Min Act: -0.0001

Data Index: 1219831 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2155. Min Act: -0.0001

Data Index: 366475 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2179. Min Act: -0.0001

Data Index: 848506 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1250860 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1343. Min Act: -0.0001

Data Index: 1084046 (C4 (Web Text))

Max Activating Token Index: 861