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

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

Neuron 1606 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: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1330931 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.9031. Min Act: -0.0001

Data Index: 998770 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1223357 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8440. Min Act: -0.0001

Data Index: 651670 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1309066 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8354. Min Act: -0.0001

Data Index: 678546 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1151087 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8243. Min Act: -0.0001

Data Index: 741631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8315. Min Act: -0.0001

Data Index: 733749 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8290. Min Act: -0.0001

Data Index: 91093 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8037. Min Act: -0.0001

Data Index: 99541 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7982. Min Act: -0.0001

Data Index: 46070 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8115. Min Act: -0.0001

Data Index: 197418 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8056. Min Act: -0.0001

Data Index: 560064 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7987. Min Act: -0.0001

Data Index: 1327733 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7990. Min Act: -0.0001

Data Index: 565633 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7959. Min Act: -0.0001

Data Index: 277076 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8083. Min Act: -0.0001

Data Index: 630640 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8040. Min Act: -0.0001

Data Index: 218056 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1141587 (C4 (Web Text))

Max Activating Token Index: 193