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

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

Neuron 4952 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: 0.9538. Min Range: -0.9538

Max Act: 0.9538. Min Act: -0.0001

Data Index: 141135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9175. Min Act: -0.0001

Data Index: 623205 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9266. Min Act: -0.0001

Data Index: 420402 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9112. Min Act: -0.0001

Data Index: 1101062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9319. Min Act: -0.0001

Data Index: 317797 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9167. Min Act: -0.0001

Data Index: 882365 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9136. Min Act: -0.0001

Data Index: 97314 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9233. Min Act: -0.0001

Data Index: 512930 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9106. Min Act: -0.0001

Data Index: 613113 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9127. Min Act: -0.0001

Data Index: 644352 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9076. Min Act: -0.0001

Data Index: 20072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1343344 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9103. Min Act: -0.0001

Data Index: 8655 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8953. Min Act: -0.0001

Data Index: 403254 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8979. Min Act: -0.0001

Data Index: 873742 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8983. Min Act: -0.0001

Data Index: 816123 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9046. Min Act: -0.0001

Data Index: 743048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9036. Min Act: -0.0001

Data Index: 121862 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9061. Min Act: -0.0001

Data Index: 213985 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9056. Min Act: -0.0001

Data Index: 427185 (C4 (Web Text))

Max Activating Token Index: 9