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

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

Neuron 1209 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: 0.7803. Min Range: -0.7803

Max Act: 0.7472. Min Act: -0.0000

Data Index: 666321 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1275727 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7803. Min Act: -0.0000

Data Index: 226720 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7266. Min Act: -0.0000

Data Index: 265308 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7151. Min Act: -0.0000

Data Index: 77840 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7120. Min Act: -0.0000

Data Index: 114669 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1186422 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6207. Min Act: -0.0000

Data Index: 528337 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6144. Min Act: -0.0000

Data Index: 318690 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5855. Min Act: -0.0000

Data Index: 531386 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5427. Min Act: -0.0000

Data Index: 270203 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5694. Min Act: -0.0000

Data Index: 106909 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5672. Min Act: -0.0000

Data Index: 720079 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5622. Min Act: 0.0000

Data Index: 52700 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5535. Min Act: -0.0000

Data Index: 530606 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5292. Min Act: 0.0000

Data Index: 665204 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5252. Min Act: -0.0000

Data Index: 239290 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1174432 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1176242 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5346. Min Act: -0.0000

Data Index: 171237 (C4 (Web Text))

Max Activating Token Index: 9