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

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

Neuron 4268 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1001929 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5230. Min Act: -0.0000

Data Index: 836706 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5375. Min Act: -0.0000

Data Index: 619449 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4594. Min Act: -0.0000

Data Index: 732778 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4788. Min Act: -0.0000

Data Index: 133736 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4374. Min Act: 0.0000

Data Index: 1072036 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4434. Min Act: -0.0000

Data Index: 942170 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4048. Min Act: -0.0000

Data Index: 754226 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4120. Min Act: -0.0000

Data Index: 545487 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1322707 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3970. Min Act: -0.0000

Data Index: 294462 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3682. Min Act: -0.0000

Data Index: 282064 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3449. Min Act: -0.0000

Data Index: 844517 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3521. Min Act: -0.0000

Data Index: 907671 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3577. Min Act: -0.0000

Data Index: 196641 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3589. Min Act: -0.0000

Data Index: 166098 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1114781 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3513. Min Act: -0.0000

Data Index: 577706 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1230025 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3155. Min Act: -0.0000

Data Index: 459266 (C4 (Web Text))

Max Activating Token Index: 171