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

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

Neuron 3186 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1504. Min Act: -0.0000

Data Index: 751962 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1148771 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1282746 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.0528. Min Act: -0.0000

Data Index: 831602 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1315201 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9855. Min Act: -0.0000

Data Index: 201796 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.1504. Min Range: -1.1504

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1105 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1320925 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1338780 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9251. Min Act: -0.0000

Data Index: 538400 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9601. Min Act: -0.0000

Data Index: 164624 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1225939 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9290. Min Act: -0.0000

Data Index: 873871 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9242. Min Act: -0.0000

Data Index: 75354 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.9034. Min Act: -0.0000

Data Index: 974069 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8936. Min Act: -0.0000

Data Index: 374196 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8896. Min Act: -0.0000

Data Index: 589103 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8249. Min Act: -0.0000

Data Index: 260868 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8065. Min Act: -0.0000

Data Index: 484747 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.1504. Min Range: -1.1504

Max Act: 0.8130. Min Act: -0.0000

Data Index: 311386 (C4 (Web Text))

Max Activating Token Index: 367