Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1349 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5415. Min Act: -0.0001

Data Index: 632018 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5501. Min Act: -0.0001

Data Index: 144315 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5294. Min Act: -0.0001

Data Index: 600712 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5482. Min Act: -0.0001

Data Index: 604508 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5432. Min Act: -0.0001

Data Index: 880985 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5050. Min Act: -0.0001

Data Index: 195606 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5316. Min Act: -0.0001

Data Index: 643579 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1339192 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4953. Min Act: -0.0001

Data Index: 605030 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4650. Min Act: -0.0001

Data Index: 429547 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1262639 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4539. Min Act: -0.0001

Data Index: 578668 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1093739 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4800. Min Act: -0.0001

Data Index: 226186 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4594. Min Act: -0.0001

Data Index: 1298508 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4553. Min Act: -0.0001

Data Index: 946939 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4271. Min Act: -0.0001

Data Index: 722986 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4653. Min Act: -0.0001

Data Index: 434068 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3934. Min Act: -0.0001

Data Index: 174388 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4536. Min Act: -0.0001

Data Index: 939922 (C4 (Web Text))

Max Activating Token Index: 149