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

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

Neuron 1376 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.6579. Min Act: -0.0000

Data Index: 3447 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.4954. Min Act: -0.0001

Data Index: 1134729 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1533960 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.4168. Min Act: -0.0001

Data Index: 698569 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1530820 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3944. Min Act: -0.0001

Data Index: 1207616 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3761. Min Act: -0.0001

Data Index: 502684 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1470829 (Python Code)

Max Activating Token Index: 981

Text #8

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.4042. Min Act: -0.0001

Data Index: 530853 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3531. Min Act: -0.0001

Data Index: 202688 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3756. Min Act: -0.0001

Data Index: 463889 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3721. Min Act: -0.0001

Data Index: 511726 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3851. Min Act: -0.0001

Data Index: 572426 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3376. Min Act: -0.0001

Data Index: 714207 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3406. Min Act: -0.0001

Data Index: 533578 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3462. Min Act: -0.0001

Data Index: 818921 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3233. Min Act: -0.0000

Data Index: 435902 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1574012 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3041. Min Act: -0.0000

Data Index: 930956 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.6579. Min Range: -0.6579

Max Act: 0.3091. Min Act: -0.0000

Data Index: 531671 (C4 (Web Text))

Max Activating Token Index: 527