Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2090 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9727. Min Act: -0.0001

Data Index: 649498 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9041. Min Act: -0.0001

Data Index: 255151 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9170. Min Act: -0.0001

Data Index: 1288176 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9150. Min Act: -0.0001

Data Index: 141211 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8895. Min Act: -0.0001

Data Index: 1019008 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9134. Min Act: -0.0001

Data Index: 126124 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9087. Min Act: -0.0001

Data Index: 302245 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9115. Min Act: -0.0001

Data Index: 490545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1312502 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9169. Min Act: -0.0001

Data Index: 100654 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8979. Min Act: -0.0001

Data Index: 159989 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8960. Min Act: -0.0001

Data Index: 394423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.9072. Min Act: -0.0001

Data Index: 584402 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8973. Min Act: -0.0001

Data Index: 85880 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8868. Min Act: -0.0001

Data Index: 1034126 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8837. Min Act: -0.0001

Data Index: 466405 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1044139 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8792. Min Act: -0.0001

Data Index: 366707 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8871. Min Act: -0.0001

Data Index: 558030 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.9727. Min Range: -0.9727

Max Act: 0.8785. Min Act: -0.0001

Data Index: 1165580 (C4 (Web Text))

Max Activating Token Index: 401