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

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

Neuron 5977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2478. Min Range: -1.2478

Max Act: 1.2478. Min Act: -0.0000

Data Index: 19672 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.2478. Min Range: -1.2478

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1101355 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1359539 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.2478. Min Range: -1.2478

Max Act: 1.0278. Min Act: -0.0000

Data Index: 663193 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1205255 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.9050. Min Act: -0.0000

Data Index: 828371 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1015306 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7850. Min Act: -0.0000

Data Index: 305031 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.8145. Min Act: -0.0000

Data Index: 408988 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1002902 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1333930 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.8378. Min Act: -0.0000

Data Index: 943644 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1357092 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1118144 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7395. Min Act: -0.0000

Data Index: 697216 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1112461 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1266788 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.6735. Min Act: -0.0000

Data Index: 186411 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7039. Min Act: -0.0000

Data Index: 790497 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 1.2478. Min Range: -1.2478

Max Act: 0.7035. Min Act: -0.0000

Data Index: 735040 (C4 (Web Text))

Max Activating Token Index: 464