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

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

Neuron 4406 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.8250. Min Act: -0.0000

Data Index: 638313 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.7991. Min Act: -0.0000

Data Index: 1599227 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.7108. Min Act: -0.0000

Data Index: 459522 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6532. Min Act: -0.0000

Data Index: 681866 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1411069 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1076494 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5665. Min Act: -0.0000

Data Index: 407452 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1133259 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1080373 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6584. Min Act: -0.0000

Data Index: 254118 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5073. Min Act: -0.0000

Data Index: 600792 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6379. Min Act: -0.0000

Data Index: 149109 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1206039 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5758. Min Act: -0.0000

Data Index: 961812 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5897. Min Act: -0.0000

Data Index: 253313 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6203. Min Act: -0.0000

Data Index: 108937 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1001915 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1545644 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.6546. Min Act: -0.0000

Data Index: 764379 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.8250. Min Range: -1.8250

Max Act: 1.5307. Min Act: -0.0000

Data Index: 674441 (C4 (Web Text))

Max Activating Token Index: 402