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

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

Neuron 2232 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.9419. Min Act: -0.0000

Data Index: 1159015 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6400. Min Act: -0.0000

Data Index: 1067828 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.5000. Min Act: -0.0000

Data Index: 260556 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.3194. Min Act: -0.0000

Data Index: 917031 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.3046. Min Act: -0.0000

Data Index: 1058013 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.1752. Min Act: -0.0000

Data Index: 2214 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.2579. Min Act: -0.0000

Data Index: 869533 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.1129. Min Act: -0.0000

Data Index: 561946 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.8882. Min Act: -0.0000

Data Index: 66266 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.9306. Min Act: -0.0000

Data Index: 753957 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.0123. Min Act: -0.0000

Data Index: 994264 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.9782. Min Act: -0.0000

Data Index: 440454 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.8781. Min Act: -0.0000

Data Index: 589572 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.0821. Min Act: -0.0000

Data Index: 942771 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1116972 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.0101. Min Act: -0.0000

Data Index: 340255 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.7087. Min Act: -0.0000

Data Index: 17554 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1218707 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.9419. Min Range: -2.9419

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1202368 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.0050. Min Act: -0.0000

Data Index: 629243 (C4 (Web Text))

Max Activating Token Index: 601