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

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

Neuron 2271 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.9235. Min Act: -0.0000

Data Index: 563988 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7937. Min Act: -0.0001

Data Index: 341760 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1316829 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6937. Min Act: -0.0001

Data Index: 1096692 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7421. Min Act: -0.0001

Data Index: 979041 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7147. Min Act: -0.0000

Data Index: 56808 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6846. Min Act: -0.0000

Data Index: 476544 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6966. Min Act: -0.0001

Data Index: 1121876 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6702. Min Act: -0.0001

Data Index: 847274 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6887. Min Act: 0.0001

Data Index: 109437 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6686. Min Act: -0.0001

Data Index: 564075 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6650. Min Act: -0.0000

Data Index: 158142 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6793. Min Act: -0.0001

Data Index: 610120 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.7048. Min Act: -0.0000

Data Index: 69491 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6758. Min Act: 0.0000

Data Index: 1152966 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6504. Min Act: -0.0001

Data Index: 764321 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6723. Min Act: -0.0000

Data Index: 694522 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6794. Min Act: -0.0001

Data Index: 239758 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6570. Min Act: 0.0001

Data Index: 829672 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.9235. Min Range: -0.9235

Max Act: 0.6542. Min Act: -0.0001

Data Index: 72247 (C4 (Web Text))

Max Activating Token Index: 250