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

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

Neuron 1212 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: 0.0124. Min Range: -0.0124

Max Act: 0.0123. Min Act: -0.0001

Data Index: 289428 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1098896 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1564728 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1496997 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 318725 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 96026 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 110940 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 469404 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 282668 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 430051 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 183729 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 204524 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 18582 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 432108 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 88884 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 151572 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 516278 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 446232 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 377492 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0120. Min Act: -0.0001

Data Index: 84362 (C4 (Web Text))

Max Activating Token Index: 1