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

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

Neuron 1607 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: 7.6534. Min Range: -7.6534

Max Act: 7.6534. Min Act: -0.0000

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 7.6534. Min Range: -7.6534

Max Act: 6.2160. Min Act: -0.0000

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.7401. Min Act: -0.0000

Data Index: 1098880 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.9533. Min Act: -0.0000

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.7543. Min Act: -0.0000

Data Index: 1263754 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.4846. Min Act: -0.0000

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.5702. Min Act: -0.0000

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.9352. Min Act: -0.0001

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.9993. Min Act: -0.0001

Data Index: 1100155 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.1796. Min Act: -0.0001

Data Index: 443827 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.8866. Min Act: -0.0000

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.0745. Min Act: -0.0000

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.0229. Min Act: -0.0001

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.8102. Min Act: -0.0000

Data Index: 240119 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 7.6534. Min Range: -7.6534

Max Act: 5.0206. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.8496. Min Act: -0.0001

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.9464. Min Act: -0.0000

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.9336. Min Act: -0.0001

Data Index: 767321 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.8651. Min Act: -0.0000

Data Index: 32697 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 7.6534. Min Range: -7.6534

Max Act: 4.6902. Min Act: -0.0000

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 330