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

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

Neuron 5097 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: 0.3404. Min Range: -0.3404

Max Act: 0.3404. Min Act: -0.0001

Data Index: 869637 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3210. Min Act: -0.0001

Data Index: 314890 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3257. Min Act: -0.0002

Data Index: 104522 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3136. Min Act: -0.0001

Data Index: 672519 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3149. Min Act: -0.0001

Data Index: 1215273 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3293. Min Act: -0.0001

Data Index: 122397 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3209. Min Act: -0.0001

Data Index: 272384 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3149. Min Act: -0.0001

Data Index: 757989 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3063. Min Act: -0.0001

Data Index: 843862 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3067. Min Act: -0.0001

Data Index: 925785 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3081. Min Act: -0.0001

Data Index: 621171 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3049. Min Act: -0.0001

Data Index: 654023 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2967. Min Act: -0.0001

Data Index: 451004 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3023. Min Act: -0.0001

Data Index: 960617 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.3066. Min Act: -0.0001

Data Index: 383518 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2898. Min Act: -0.0001

Data Index: 521869 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1133316 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1009176 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2879. Min Act: -0.0001

Data Index: 880044 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2981. Min Act: -0.0001

Data Index: 109713 (C4 (Web Text))

Max Activating Token Index: 323