Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0002

Data Index: 708435 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6244. Min Act: -0.0002

Data Index: 1113568 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6143. Min Act: -0.0002

Data Index: 1130534 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6150. Min Act: -0.0002

Data Index: 887864 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5922. Min Act: -0.0002

Data Index: 490064 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5896. Min Act: -0.0002

Data Index: 540263 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5721. Min Act: -0.0002

Data Index: 950471 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5692. Min Act: -0.0002

Data Index: 1337256 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5602. Min Act: -0.0002

Data Index: 1203749 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5659. Min Act: -0.0002

Data Index: 721151 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5731. Min Act: -0.0002

Data Index: 1192799 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5473. Min Act: -0.0002

Data Index: 836275 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5646. Min Act: -0.0002

Data Index: 261107 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5520. Min Act: -0.0002

Data Index: 71541 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5470. Min Act: -0.0002

Data Index: 777870 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5493. Min Act: -0.0002

Data Index: 133947 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5368. Min Act: -0.0002

Data Index: 1171228 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5256. Min Act: -0.0002

Data Index: 170436 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5337. Min Act: -0.0002

Data Index: 752261 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5232. Min Act: -0.0002

Data Index: 1247542 (C4 (Web Text))

Max Activating Token Index: 89