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

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

Neuron 2486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.2258. Min Act: -0.0001

Data Index: 1131139 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.1148. Min Act: -0.0001

Data Index: 427192 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.0592. Min Act: -0.0001

Data Index: 375307 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.0445. Min Act: -0.0001

Data Index: 592389 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9860. Min Act: -0.0001

Data Index: 1230357 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9799. Min Act: -0.0001

Data Index: 1294045 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8946. Min Act: -0.0001

Data Index: 250358 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1355433 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9413. Min Act: -0.0001

Data Index: 810396 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9072. Min Act: -0.0001

Data Index: 634678 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.2258. Min Range: -1.2258

Max Act: 1.0748. Min Act: -0.0001

Data Index: 276333 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9254. Min Act: -0.0001

Data Index: 724889 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.9398. Min Act: -0.0001

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8257. Min Act: -0.0001

Data Index: 657170 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8758. Min Act: -0.0001

Data Index: 1355304 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1220178 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8663. Min Act: -0.0001

Data Index: 180319 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1285345 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8840. Min Act: -0.0001

Data Index: 194194 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.2258. Min Range: -1.2258

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1602194 (Python Code)

Max Activating Token Index: 849