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

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

Neuron 684 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: 0.3654. Min Range: -0.3654

Max Act: 0.3654. Min Act: -0.0000

Data Index: 467970 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1227792 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3372. Min Act: -0.0000

Data Index: 537929 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3143. Min Act: -0.0000

Data Index: 807032 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3169. Min Act: -0.0000

Data Index: 202755 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1043421 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2997. Min Act: -0.0000

Data Index: 106679 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2739. Min Act: -0.0000

Data Index: 980669 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2438. Min Act: -0.0000

Data Index: 287226 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2544. Min Act: -0.0000

Data Index: 716012 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2443. Min Act: -0.0000

Data Index: 153306 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1166351 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1637213 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2491. Min Act: -0.0000

Data Index: 52958 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2481. Min Act: -0.0000

Data Index: 459975 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2484. Min Act: -0.0000

Data Index: 329076 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2587. Min Act: -0.0000

Data Index: 275776 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2332. Min Act: -0.0000

Data Index: 361690 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1341937 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 842