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

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

Neuron 1322 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0190. Min Range: -3.0190

Max Act: 3.0190. Min Act: -0.0000

Data Index: 1332083 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.9490. Min Act: -0.0000

Data Index: 85147 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.4110. Min Act: -0.0001

Data Index: 1243112 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.4342. Min Act: -0.0000

Data Index: 82889 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.3032. Min Act: -0.0001

Data Index: 164834 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.2775. Min Act: -0.0001

Data Index: 470434 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.3004. Min Act: -0.0000

Data Index: 921159 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.2816. Min Act: -0.0001

Data Index: 894941 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.0535. Min Act: -0.0001

Data Index: 769602 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.0115. Min Act: -0.0001

Data Index: 623057 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 3.0190. Min Range: -3.0190

Max Act: 1.9458. Min Act: -0.0001

Data Index: 636349 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.0566. Min Act: -0.0001

Data Index: 135545 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.0319. Min Act: -0.0001

Data Index: 583316 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.1151. Min Act: -0.0001

Data Index: 1216302 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 3.0190. Min Range: -3.0190

Max Act: 1.5803. Min Act: -0.0001

Data Index: 167751 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.0996. Min Act: -0.0000

Data Index: 153298 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 3.0190. Min Range: -3.0190

Max Act: 1.8434. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 3.0190. Min Range: -3.0190

Max Act: 1.7479. Min Act: -0.0001

Data Index: 984916 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.0190. Min Range: -3.0190

Max Act: 2.1415. Min Act: -0.0001

Data Index: 818278 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.0190. Min Range: -3.0190

Max Act: 1.9806. Min Act: -0.0001

Data Index: 1206160 (C4 (Web Text))

Max Activating Token Index: 40