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

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

Neuron 2567 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1347. Min Range: -3.1347

Max Act: 3.1347. Min Act: -0.0001

Data Index: 296649 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.1347. Min Range: -3.1347

Max Act: 3.0583. Min Act: -0.0001

Data Index: 1020485 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.6269. Min Act: -0.0000

Data Index: 867487 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8519. Min Act: -0.0001

Data Index: 283494 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8220. Min Act: -0.0001

Data Index: 334191 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.9044. Min Act: -0.0001

Data Index: 1266414 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8350. Min Act: -0.0001

Data Index: 762206 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.6944. Min Act: -0.0001

Data Index: 434979 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.7715. Min Act: -0.0001

Data Index: 1022190 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.5544. Min Act: -0.0001

Data Index: 1197023 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.5933. Min Act: -0.0001

Data Index: 917120 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.6604. Min Act: -0.0001

Data Index: 221649 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.5156. Min Act: -0.0000

Data Index: 794480 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.3400. Min Act: -0.0000

Data Index: 1229486 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.2882. Min Act: -0.0001

Data Index: 216401 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.1216. Min Act: -0.0001

Data Index: 290630 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9905. Min Act: -0.0001

Data Index: 274076 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.1659. Min Act: -0.0001

Data Index: 504972 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.3529. Min Act: -0.0000

Data Index: 289884 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.1297. Min Act: -0.0001

Data Index: 877208 (C4 (Web Text))

Max Activating Token Index: 364