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

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

Neuron 3035 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.6491. Min Act: -0.0000

Data Index: 818364 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.6444. Min Act: -0.0000

Data Index: 13717 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.6393. Min Act: -0.0000

Data Index: 495701 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1004832 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1257183 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1316414 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1300850 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5011. Min Act: -0.0000

Data Index: 169314 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5113. Min Act: -0.0000

Data Index: 19123 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5032. Min Act: -0.0000

Data Index: 644984 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1147985 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4803. Min Act: -0.0000

Data Index: 572249 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4940. Min Act: -0.0000

Data Index: 826264 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5009. Min Act: -0.0000

Data Index: 456460 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4912. Min Act: -0.0000

Data Index: 990759 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4736. Min Act: -0.0000

Data Index: 359801 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1138645 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4837. Min Act: -0.0000

Data Index: 610943 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1233734 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4782. Min Act: -0.0000

Data Index: 728077 (C4 (Web Text))

Max Activating Token Index: 92