Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.4315. Min Act: -0.0000

Data Index: 56387 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.3988. Min Act: -0.0000

Data Index: 789118 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.3598. Min Act: -0.0000

Data Index: 110153 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.3447. Min Act: -0.0000

Data Index: 1297293 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.2544. Min Act: -0.0000

Data Index: 394040 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1999. Min Act: -0.0000

Data Index: 796644 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1815. Min Act: -0.0000

Data Index: 51141 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.2731. Min Act: -0.0000

Data Index: 831151 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1089. Min Act: -0.0000

Data Index: 1351208 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1021. Min Act: -0.0000

Data Index: 1318355 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 2.4315. Min Range: -2.4315

Max Act: 1.9850. Min Act: -0.0000

Data Index: 1016186 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1762. Min Act: -0.0000

Data Index: 1335905 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1668. Min Act: -0.0000

Data Index: 981792 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.0446. Min Act: -0.0000

Data Index: 159811 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.0483. Min Act: -0.0000

Data Index: 260789 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1012173 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.4315. Min Range: -2.4315

Max Act: 1.9593. Min Act: -0.0000

Data Index: 1473078 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1341789 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.0203. Min Act: -0.0000

Data Index: 605543 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.4315. Min Range: -2.4315

Max Act: 2.0150. Min Act: -0.0000

Data Index: 1336270 (C4 (Web Text))

Max Activating Token Index: 684