Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1156752 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.3115. Min Act: -0.0001

Data Index: 487026 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2593. Min Act: -0.0001

Data Index: 1140797 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1040722 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2834. Min Act: -0.0001

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2661. Min Act: -0.0001

Data Index: 484734 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2483. Min Act: -0.0001

Data Index: 755661 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2377. Min Act: -0.0001

Data Index: 313680 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2523. Min Act: -0.0001

Data Index: 872389 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2306. Min Act: -0.0001

Data Index: 995877 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1223754 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2467. Min Act: -0.0001

Data Index: 598072 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1267854 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1288382 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2402. Min Act: -0.0001

Data Index: 1083270 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2187. Min Act: -0.0001

Data Index: 845737 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2348. Min Act: -0.0001

Data Index: 155690 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2354. Min Act: -0.0001

Data Index: 927184 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.3745. Min Range: -0.3745

Max Act: 0.2346. Min Act: -0.0001

Data Index: 326135 (C4 (Web Text))

Max Activating Token Index: 158