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

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

Neuron 80 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: 1.1608. Min Range: -1.1608

Max Act: 1.1118. Min Act: -0.0000

Data Index: 201472 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 1.1608. Min Range: -1.1608

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1162913 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.1608. Min Range: -1.1608

Max Act: 1.0286. Min Act: -0.0000

Data Index: 911091 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.1608. Min Range: -1.1608

Max Act: 1.0988. Min Act: 0.0000

Data Index: 245560 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.1608. Min Range: -1.1608

Max Act: 1.0226. Min Act: -0.0000

Data Index: 323755 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.9501. Min Act: -0.0000

Data Index: 580901 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8821. Min Act: -0.0000

Data Index: 462619 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.9668. Min Act: -0.0000

Data Index: 145747 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.9061. Min Act: -0.0000

Data Index: 129913 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8682. Min Act: 0.0000

Data Index: 371868 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8293. Min Act: -0.0000

Data Index: 413626 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.9052. Min Act: -0.0000

Data Index: 861766 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1045077 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8654. Min Act: -0.0000

Data Index: 242720 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8645. Min Act: -0.0000

Data Index: 780835 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8312. Min Act: -0.0000

Data Index: 789938 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8583. Min Act: -0.0000

Data Index: 876736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8847. Min Act: 0.0000

Data Index: 1301907 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8546. Min Act: 0.0000

Data Index: 1324900 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.1608. Min Range: -1.1608

Max Act: 0.8210. Min Act: -0.0000

Data Index: 11408 (C4 (Web Text))

Max Activating Token Index: 938