Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3078 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0000

Data Index: 591511 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1301305 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1090002 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1246108 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1187884 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1375539 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6740. Min Act: -0.0000

Data Index: 622565 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1184788 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6949. Min Act: -0.0000

Data Index: 783152 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1644229 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1737665 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1200555 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1551614 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1116589 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6050. Min Act: -0.0000

Data Index: 527402 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1632561 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5520. Min Act: -0.0000

Data Index: 986357 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1935132 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1192057 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5378. Min Act: -0.0000

Data Index: 243395 (The Pile)

Max Activating Token Index: 99