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

Dataset: The Pile

Neuron 3159 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: 0.8084. Min Range: -0.8084

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1980037 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6844. Min Act: -0.0000

Data Index: 687115 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1746288 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1836919 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1391371 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6798. Min Act: -0.0000

Data Index: 862514 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1015578 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6711. Min Act: -0.0000

Data Index: 902576 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5784. Min Act: -0.0000

Data Index: 205038 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1379820 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1524901 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6313. Min Act: -0.0000

Data Index: 187407 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1710634 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5826. Min Act: -0.0000

Data Index: 484096 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1799245 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6002. Min Act: -0.0000

Data Index: 129166 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5963. Min Act: -0.0000

Data Index: 714518 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1689316 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.5313. Min Act: -0.0000

Data Index: 445593 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.8084. Min Range: -0.8084

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1368093 (The Pile)

Max Activating Token Index: 908