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

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

Neuron 136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0002

Data Index: 226998 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0582. Min Act: -0.0002

Data Index: 14733 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0533. Min Act: -0.0002

Data Index: 500670 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0496. Min Act: -0.0002

Data Index: 179105 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0504. Min Act: -0.0002

Data Index: 685549 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1102841 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0455. Min Act: -0.0002

Data Index: 179342 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0460. Min Act: -0.0002

Data Index: 351205 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1641224 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1408198 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0432. Min Act: -0.0002

Data Index: 810357 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1085344 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0423. Min Act: -0.0002

Data Index: 140277 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0439. Min Act: -0.0002

Data Index: 330904 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0430. Min Act: -0.0002

Data Index: 865745 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0435. Min Act: -0.0002

Data Index: 559258 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1578246 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0424. Min Act: -0.0002

Data Index: 489230 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1457222 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0418. Min Act: -0.0002

Data Index: 308856 (C4 (Web Text))

Max Activating Token Index: 261