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

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

Neuron 4071 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: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0001

Data Index: 242733 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0001

Data Index: 76436 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0140. Min Act: -0.0001

Data Index: 192360 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0001

Data Index: 694270 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0001

Data Index: 777091 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0001

Data Index: 960554 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0001

Data Index: 135354 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1167892 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0001

Data Index: 416762 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0001

Data Index: 935613 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0001

Data Index: 450295 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0001

Data Index: 567786 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0001

Data Index: 50203 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0001

Data Index: 726991 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0001

Data Index: 132398 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0001

Data Index: 701539 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0001

Data Index: 486091 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0123. Min Act: -0.0001

Data Index: 331089 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0124. Min Act: -0.0001

Data Index: 922239 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0124. Min Act: -0.0001

Data Index: 527880 (C4 (Web Text))

Max Activating Token Index: 586