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

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

Neuron 2147 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8368. Min Act: -0.0001

Data Index: 691868 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1476096 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8532. Min Act: -0.0001

Data Index: 1438656 (Python Code)

Max Activating Token Index: 566

Text #3

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7954. Min Act: -0.0001

Data Index: 244730 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7738. Min Act: -0.0001

Data Index: 744353 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1608382 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7823. Min Act: -0.0001

Data Index: 968414 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7514. Min Act: -0.0001

Data Index: 1401516 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1632194 (Python Code)

Max Activating Token Index: 159

Text #9

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7956. Min Act: -0.0001

Data Index: 37362 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7886. Min Act: -0.0001

Data Index: 1384770 (Python Code)

Max Activating Token Index: 295

Text #11

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7926. Min Act: -0.0002

Data Index: 179388 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1546932 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1419979 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1082460 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7456. Min Act: -0.0002

Data Index: 1058175 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7488. Min Act: -0.0001

Data Index: 1445615 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8186. Min Act: -0.0001

Data Index: 69406 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7495. Min Act: -0.0001

Data Index: 1504479 (Python Code)

Max Activating Token Index: 965

Text #19

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7224. Min Act: -0.0002

Data Index: 1063579 (C4 (Web Text))

Max Activating Token Index: 54