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

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

Neuron 909 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.8030. Min Act: -0.0001

Data Index: 478845 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.7156. Min Act: -0.0001

Data Index: 29481 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6899. Min Act: -0.0001

Data Index: 583497 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.7071. Min Act: -0.0001

Data Index: 77660 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.7131. Min Act: -0.0001

Data Index: 928599 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6931. Min Act: -0.0001

Data Index: 468181 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6722. Min Act: -0.0001

Data Index: 991847 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6480. Min Act: -0.0001

Data Index: 1308526 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6678. Min Act: -0.0001

Data Index: 580948 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6443. Min Act: -0.0001

Data Index: 306869 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6561. Min Act: -0.0001

Data Index: 1202654 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6808. Min Act: -0.0001

Data Index: 650422 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6390. Min Act: -0.0001

Data Index: 870178 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1156899 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6761. Min Act: -0.0001

Data Index: 534363 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1033249 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6555. Min Act: -0.0001

Data Index: 733576 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6555. Min Act: -0.0001

Data Index: 356900 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6453. Min Act: -0.0001

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6217. Min Act: -0.0001

Data Index: 492734 (C4 (Web Text))

Max Activating Token Index: 222