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

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

Neuron 1671 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: 8.6149. Min Range: -8.6149

Max Act: 8.6149. Min Act: -0.0000

Data Index: 382012 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 8.6149. Min Range: -8.6149

Max Act: 8.2147. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 8.6149. Min Range: -8.6149

Max Act: 7.4441. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 8.6149. Min Range: -8.6149

Max Act: 8.0901. Min Act: -0.0001

Data Index: 1322952 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 8.6149. Min Range: -8.6149

Max Act: 7.4796. Min Act: -0.0001

Data Index: 725306 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 8.6149. Min Range: -8.6149

Max Act: 6.8020. Min Act: -0.0001

Data Index: 309108 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 8.6149. Min Range: -8.6149

Max Act: 6.0701. Min Act: -0.0001

Data Index: 493031 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 8.6149. Min Range: -8.6149

Max Act: 6.6012. Min Act: -0.0001

Data Index: 1314358 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 8.6149. Min Range: -8.6149

Max Act: 6.5113. Min Act: -0.0001

Data Index: 1232595 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 8.6149. Min Range: -8.6149

Max Act: 6.9619. Min Act: -0.0000

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.7536. Min Act: -0.0001

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.5305. Min Act: -0.0001

Data Index: 290201 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 8.6149. Min Range: -8.6149

Max Act: 2.9394. Min Act: -0.0001

Data Index: 141348 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.4543. Min Act: -0.0000

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.2844. Min Act: -0.0001

Data Index: 230893 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.0316. Min Act: -0.0001

Data Index: 291272 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.8342. Min Act: -0.0001

Data Index: 855962 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 8.6149. Min Range: -8.6149

Max Act: 4.2088. Min Act: -0.0001

Data Index: 395810 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 8.6149. Min Range: -8.6149

Max Act: 3.8709. Min Act: -0.0000

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 8.6149. Min Range: -8.6149

Max Act: 5.0259. Min Act: -0.0001

Data Index: 777285 (C4 (Web Text))

Max Activating Token Index: 70