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

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

Neuron 5749 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1218988 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7032. Min Act: -0.0000

Data Index: 951374 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6763. Min Act: -0.0000

Data Index: 499810 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6237. Min Act: -0.0000

Data Index: 946376 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1201329 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6231. Min Act: -0.0000

Data Index: 126147 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5977. Min Act: -0.0000

Data Index: 901539 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1072488 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1253179 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5756. Min Act: -0.0000

Data Index: 67076 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1132866 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1231525 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1117441 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5185. Min Act: -0.0000

Data Index: 763549 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1278786 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5325. Min Act: -0.0000

Data Index: 634257 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1126359 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5319. Min Act: -0.0000

Data Index: 937519 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.4725. Min Act: -0.0000

Data Index: 273778 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1093926 (C4 (Web Text))

Max Activating Token Index: 243