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

Dataset: The Pile

Neuron 3384 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8626. Min Act: -0.0000

Data Index: 683144 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1446386 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7943. Min Act: -0.0000

Data Index: 102406 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1748000 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1451706 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1528334 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6776. Min Act: -0.0000

Data Index: 600697 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6300. Min Act: -0.0000

Data Index: 817493 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7003. Min Act: -0.0000

Data Index: 123427 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6449. Min Act: -0.0000

Data Index: 784380 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6206. Min Act: -0.0000

Data Index: 949619 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6074. Min Act: -0.0000

Data Index: 32387 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6304. Min Act: -0.0000

Data Index: 221818 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1250340 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6422. Min Act: -0.0000

Data Index: 556586 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1042718 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6322. Min Act: -0.0000

Data Index: 713216 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1840254 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.6504. Min Act: -0.0000

Data Index: 341789 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.5767. Min Act: -0.0000

Data Index: 491870 (The Pile)

Max Activating Token Index: 915