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

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

Neuron 3392 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.7213. Min Act: -0.0001

Data Index: 1354254 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.0949. Min Act: -0.0001

Data Index: 146798 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.0925. Min Act: -0.0001

Data Index: 1336965 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1028. Min Act: -0.0001

Data Index: 1011750 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.0634. Min Act: -0.0001

Data Index: 590249 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.7213. Min Range: -1.7213

Max Act: 1.1059. Min Act: -0.0001

Data Index: 963282 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9605. Min Act: -0.0001

Data Index: 1107381 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9397. Min Act: -0.0001

Data Index: 151650 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9384. Min Act: -0.0001

Data Index: 201005 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9756. Min Act: -0.0001

Data Index: 235054 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.8946. Min Act: -0.0001

Data Index: 196902 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9703. Min Act: -0.0001

Data Index: 201696 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9750. Min Act: -0.0001

Data Index: 858569 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.8429. Min Act: -0.0001

Data Index: 856446 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.8657. Min Act: -0.0001

Data Index: 920309 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9419. Min Act: -0.0001

Data Index: 519763 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9028. Min Act: -0.0001

Data Index: 101890 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9020. Min Act: -0.0001

Data Index: 471150 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1231142 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.7213. Min Range: -1.7213

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1076167 (C4 (Web Text))

Max Activating Token Index: 884