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

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

Neuron 1043 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: 1.6592. Min Range: -1.6592

Max Act: 1.6592. Min Act: -0.0001

Data Index: 1277845 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.3671. Min Act: -0.0001

Data Index: 66900 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.4140. Min Act: -0.0001

Data Index: 1320069 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.3216. Min Act: -0.0001

Data Index: 1276652 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.3249. Min Act: -0.0001

Data Index: 51923 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2949. Min Act: -0.0001

Data Index: 1186197 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2508. Min Act: -0.0001

Data Index: 949384 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.3057. Min Act: -0.0001

Data Index: 769265 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.3813. Min Act: -0.0001

Data Index: 490909 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.4639. Min Act: -0.0001

Data Index: 578549 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2264. Min Act: -0.0001

Data Index: 1180137 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2831. Min Act: -0.0001

Data Index: 982610 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.1963. Min Act: -0.0001

Data Index: 16317 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.1841. Min Act: -0.0001

Data Index: 410112 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.1475. Min Act: -0.0001

Data Index: 434801 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2179. Min Act: -0.0001

Data Index: 1312198 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2381. Min Act: -0.0001

Data Index: 1115139 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.0796. Min Act: -0.0001

Data Index: 127045 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.2203. Min Act: -0.0001

Data Index: 1222881 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.6592. Min Range: -1.6592

Max Act: 1.1568. Min Act: -0.0001

Data Index: 472237 (C4 (Web Text))

Max Activating Token Index: 448