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

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

Neuron 2092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8965. Min Act: -0.0001

Data Index: 268774 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1035252 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8782. Min Act: -0.0001

Data Index: 903118 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7860. Min Act: -0.0001

Data Index: 43940 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7002. Min Act: -0.0001

Data Index: 363443 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7091. Min Act: -0.0001

Data Index: 393639 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1254133 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6886. Min Act: -0.0001

Data Index: 676015 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6827. Min Act: -0.0001

Data Index: 89752 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7168. Min Act: -0.0001

Data Index: 156417 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6710. Min Act: -0.0001

Data Index: 893247 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1333114 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6874. Min Act: -0.0001

Data Index: 722567 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5941. Min Act: -0.0001

Data Index: 1262663 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6615. Min Act: -0.0001

Data Index: 335221 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7006. Min Act: -0.0001

Data Index: 1106635 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6998. Min Act: -0.0001

Data Index: 760464 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6331. Min Act: -0.0001

Data Index: 26368 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6183. Min Act: -0.0001

Data Index: 808623 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6319. Min Act: -0.0001

Data Index: 650206 (C4 (Web Text))

Max Activating Token Index: 696