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

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

Neuron 4181 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: 1.6657. Min Range: -1.6657

Max Act: 1.6657. Min Act: -0.0000

Data Index: 197597 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.4668. Min Act: -0.0000

Data Index: 196459 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.4111. Min Act: -0.0000

Data Index: 27195 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1068193 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1264349 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2475. Min Act: -0.0000

Data Index: 254948 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1182695 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.3482. Min Act: -0.0000

Data Index: 13374 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1174903 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2253. Min Act: -0.0000

Data Index: 312904 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2135. Min Act: -0.0000

Data Index: 387223 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1099648 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2432. Min Act: -0.0000

Data Index: 751569 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.2285. Min Act: -0.0000

Data Index: 818522 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1263592 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.0955. Min Act: -0.0000

Data Index: 382600 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1054289 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.1468. Min Act: -0.0000

Data Index: 109538 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.1064. Min Act: -0.0000

Data Index: 433402 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.6657. Min Range: -1.6657

Max Act: 1.0944. Min Act: -0.0000

Data Index: 515278 (C4 (Web Text))

Max Activating Token Index: 841