Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4921 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0425. Min Range: -1.0425

Max Act: 1.0425. Min Act: -0.0001

Data Index: 480820 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9633. Min Act: -0.0001

Data Index: 472676 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.0425. Min Range: -1.0425

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1053213 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9076. Min Act: -0.0001

Data Index: 618644 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8508. Min Act: -0.0001

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9411. Min Act: -0.0001

Data Index: 721988 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9275. Min Act: -0.0001

Data Index: 349732 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9135. Min Act: -0.0001

Data Index: 54121 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8976. Min Act: -0.0001

Data Index: 526136 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8242. Min Act: -0.0001

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9159. Min Act: -0.0001

Data Index: 1221898 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9395. Min Act: -0.0001

Data Index: 677591 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1143700 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9809. Min Act: -0.0001

Data Index: 1000441 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9042. Min Act: -0.0001

Data Index: 1015282 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9272. Min Act: -0.0001

Data Index: 303715 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8827. Min Act: -0.0001

Data Index: 382578 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8542. Min Act: -0.0001

Data Index: 638849 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8171. Min Act: -0.0001

Data Index: 485375 (C4 (Web Text))

Max Activating Token Index: 221