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

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

Neuron 2519 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0000

Data Index: 495006 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8164. Min Act: -0.0001

Data Index: 141431 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7376. Min Act: -0.0001

Data Index: 942538 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7304. Min Act: -0.0000

Data Index: 749950 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6847. Min Act: -0.0000

Data Index: 482372 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1026672 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1096514 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7010. Min Act: -0.0000

Data Index: 951278 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1209753 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1301445 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6552. Min Act: -0.0000

Data Index: 558811 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6746. Min Act: -0.0000

Data Index: 980532 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6616. Min Act: -0.0000

Data Index: 34023 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6011. Min Act: -0.0000

Data Index: 917879 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6445. Min Act: -0.0000

Data Index: 698892 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1002694 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1169967 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6565. Min Act: -0.0000

Data Index: 952593 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6231. Min Act: -0.0000

Data Index: 844842 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5761. Min Act: -0.0001

Data Index: 438163 (C4 (Web Text))

Max Activating Token Index: 636