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

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

Neuron 2670 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: 0.0711. Min Range: -0.0711

Max Act: 0.0696. Min Act: -0.0001

Data Index: 646714 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0001

Data Index: 434859 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1223367 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0667. Min Act: -0.0001

Data Index: 384262 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0644. Min Act: -0.0001

Data Index: 268805 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0638. Min Act: -0.0001

Data Index: 527228 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1126428 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0624. Min Act: -0.0001

Data Index: 869702 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1127004 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0621. Min Act: -0.0001

Data Index: 910440 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0613. Min Act: -0.0001

Data Index: 594726 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0626. Min Act: -0.0001

Data Index: 703169 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1113248 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0613. Min Act: -0.0001

Data Index: 637944 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1344664 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0613. Min Act: -0.0001

Data Index: 149603 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0606. Min Act: -0.0001

Data Index: 421313 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0595. Min Act: -0.0001

Data Index: 29065 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0616. Min Act: -0.0001

Data Index: 112833 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0603. Min Act: -0.0001

Data Index: 124089 (C4 (Web Text))

Max Activating Token Index: 855