Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5326. Min Act: -0.0000

Data Index: 434779 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.5174. Min Act: -0.0000

Data Index: 427205 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4830. Min Act: -0.0000

Data Index: 788644 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1339713 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4755. Min Act: -0.0000

Data Index: 945038 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4503. Min Act: -0.0000

Data Index: 431313 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4458. Min Act: -0.0000

Data Index: 82890 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4140. Min Act: -0.0000

Data Index: 669395 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1288924 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4337. Min Act: -0.0001

Data Index: 1250415 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4338. Min Act: -0.0000

Data Index: 150646 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1108633 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1262922 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4280. Min Act: -0.0001

Data Index: 192840 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1219399 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4599. Min Act: -0.0000

Data Index: 492183 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4036. Min Act: -0.0000

Data Index: 344684 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4134. Min Act: -0.0001

Data Index: 564195 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1076008 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.5326. Min Range: -0.5326

Max Act: 0.4262. Min Act: -0.0001

Data Index: 363522 (C4 (Web Text))

Max Activating Token Index: 937