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

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

Neuron 6037 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: 0.7136. Min Range: -0.7136

Max Act: 0.7136. Min Act: -0.0001

Data Index: 570105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6871. Min Act: -0.0001

Data Index: 495814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6755. Min Act: -0.0001

Data Index: 70485 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6739. Min Act: -0.0001

Data Index: 415983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6659. Min Act: -0.0001

Data Index: 366263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6699. Min Act: -0.0001

Data Index: 756829 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1325226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6653. Min Act: -0.0001

Data Index: 280018 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6547. Min Act: -0.0001

Data Index: 208991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1179859 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6440. Min Act: -0.0001

Data Index: 609925 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6391. Min Act: -0.0001

Data Index: 805531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6280. Min Act: -0.0001

Data Index: 371640 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6335. Min Act: -0.0001

Data Index: 610891 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6260. Min Act: -0.0001

Data Index: 948837 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6268. Min Act: -0.0001

Data Index: 863492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6166. Min Act: -0.0001

Data Index: 734207 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6143. Min Act: -0.0001

Data Index: 684540 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6250. Min Act: -0.0001

Data Index: 913794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6207. Min Act: -0.0001

Data Index: 932380 (C4 (Web Text))

Max Activating Token Index: 89