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

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

Neuron 5804 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: 0.4377. Min Range: -0.4377

Max Act: 0.4344. Min Act: -0.0001

Data Index: 707187 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1024972 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4377. Min Act: -0.0001

Data Index: 1291408 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4196. Min Act: -0.0001

Data Index: 21012 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1116646 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4096. Min Act: -0.0001

Data Index: 220957 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4056. Min Act: -0.0001

Data Index: 562057 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4031. Min Act: -0.0001

Data Index: 670977 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3995. Min Act: -0.0001

Data Index: 1347133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4041. Min Act: -0.0001

Data Index: 668884 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.4017. Min Act: -0.0001

Data Index: 539664 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3998. Min Act: -0.0001

Data Index: 1024851 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3966. Min Act: -0.0001

Data Index: 719706 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3924. Min Act: -0.0001

Data Index: 34877 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1109583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1062435 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3949. Min Act: -0.0001

Data Index: 446936 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1319234 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3935. Min Act: -0.0001

Data Index: 50064 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.4377. Min Range: -0.4377

Max Act: 0.3919. Min Act: -0.0001

Data Index: 407704 (C4 (Web Text))

Max Activating Token Index: 7