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

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

Neuron 1132 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: 1.6252. Min Range: -1.6252

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1093793 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3532. Min Act: -0.0000

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4989. Min Act: -0.0000

Data Index: 390126 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1206608 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1116902 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4760. Min Act: -0.0000

Data Index: 560338 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3617. Min Act: -0.0000

Data Index: 155595 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1194497 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1131481 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4050. Min Act: -0.0000

Data Index: 742272 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4053. Min Act: -0.0000

Data Index: 592814 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1082914 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1243159 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4450. Min Act: -0.0000

Data Index: 217641 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.4321. Min Act: -0.0000

Data Index: 309923 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3004. Min Act: -0.0000

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3271. Min Act: -0.0000

Data Index: 127949 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1225274 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1578789 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3150. Min Act: -0.0000

Data Index: 847274 (C4 (Web Text))

Max Activating Token Index: 516