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

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

Neuron 1431 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: 1.9419. Min Range: -1.9419

Max Act: 1.9419. Min Act: -0.0002

Data Index: 1288554 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.8671. Min Act: -0.0002

Data Index: 301885 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7463. Min Act: -0.0002

Data Index: 227753 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6998. Min Act: -0.0002

Data Index: 152047 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7325. Min Act: -0.0002

Data Index: 18583 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6461. Min Act: -0.0002

Data Index: 439425 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6208. Min Act: -0.0002

Data Index: 694325 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6246. Min Act: -0.0002

Data Index: 1005443 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5839. Min Act: -0.0002

Data Index: 743807 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5410. Min Act: -0.0002

Data Index: 1269071 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5822. Min Act: -0.0002

Data Index: 677522 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5490. Min Act: -0.0002

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5036. Min Act: -0.0002

Data Index: 716007 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5068. Min Act: -0.0002

Data Index: 613776 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5081. Min Act: -0.0002

Data Index: 201274 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5000. Min Act: -0.0002

Data Index: 195093 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5085. Min Act: -0.0002

Data Index: 1303499 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4505. Min Act: -0.0002

Data Index: 1061557 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4375. Min Act: -0.0002

Data Index: 625790 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4349. Min Act: -0.0002

Data Index: 1096942 (C4 (Web Text))

Max Activating Token Index: 715