Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2072 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1137008 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5799. Min Act: -0.0001

Data Index: 947751 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5520. Min Act: -0.0001

Data Index: 465687 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5643. Min Act: -0.0001

Data Index: 594453 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5187. Min Act: -0.0001

Data Index: 182127 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1228601 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1016009 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5447. Min Act: -0.0001

Data Index: 1323850 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5397. Min Act: -0.0001

Data Index: 757975 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5320. Min Act: -0.0001

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5312. Min Act: -0.0001

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5283. Min Act: -0.0001

Data Index: 995894 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5091. Min Act: -0.0001

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5396. Min Act: -0.0001

Data Index: 592615 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5550. Min Act: -0.0001

Data Index: 797405 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.4939. Min Act: -0.0001

Data Index: 438340 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1192745 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.4970. Min Act: -0.0001

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.5799. Min Range: -0.5799

Max Act: 0.5134. Min Act: -0.0001

Data Index: 99268 (C4 (Web Text))

Max Activating Token Index: 909