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

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

Neuron 4361 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: 2.7284. Min Range: -2.7284

Max Act: 2.7284. Min Act: -0.0000

Data Index: 1328550 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.6989. Min Act: -0.0000

Data Index: 6400 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.4814. Min Act: -0.0000

Data Index: 21694 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.5676. Min Act: -0.0000

Data Index: 451326 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.3842. Min Act: -0.0000

Data Index: 1214364 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.2796. Min Act: -0.0000

Data Index: 1243969 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.2560. Min Act: -0.0000

Data Index: 1048975 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.3574. Min Act: -0.0000

Data Index: 250464 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.1386. Min Act: -0.0000

Data Index: 1252220 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0344. Min Act: -0.0000

Data Index: 1296387 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.3452. Min Act: -0.0000

Data Index: 931518 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.1137. Min Act: -0.0000

Data Index: 1121491 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0971. Min Act: -0.0000

Data Index: 1056582 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0986. Min Act: -0.0000

Data Index: 268523 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0953. Min Act: -0.0000

Data Index: 908968 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0359. Min Act: -0.0000

Data Index: 237087 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.7284. Min Range: -2.7284

Max Act: 1.9322. Min Act: -0.0000

Data Index: 467141 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 2.7284. Min Range: -2.7284

Max Act: 2.0939. Min Act: -0.0000

Data Index: 1323114 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 2.7284. Min Range: -2.7284

Max Act: 1.9537. Min Act: -0.0000

Data Index: 809000 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 2.7284. Min Range: -2.7284

Max Act: 1.8918. Min Act: -0.0000

Data Index: 705452 (C4 (Web Text))

Max Activating Token Index: 771