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

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

Neuron 3214 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.1754. Min Act: -0.0000

Data Index: 7336 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.4960. Min Act: -0.0000

Data Index: 302493 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.5137. Min Act: -0.0000

Data Index: 463054 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.2636. Min Act: -0.0000

Data Index: 543000 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.0981. Min Act: -0.0000

Data Index: 1228092 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.1938. Min Act: -0.0000

Data Index: 663475 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.7936. Min Act: -0.0000

Data Index: 1342077 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.0645. Min Act: -0.0000

Data Index: 833201 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.5137. Min Range: -3.5137

Max Act: 3.0621. Min Act: -0.0000

Data Index: 107290 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.7380. Min Act: -0.0000

Data Index: 1128351 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.8815. Min Act: -0.0000

Data Index: 939818 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.8179. Min Act: -0.0000

Data Index: 79225 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.7634. Min Act: -0.0000

Data Index: 81016 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.8660. Min Act: -0.0000

Data Index: 681886 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.6984. Min Act: -0.0000

Data Index: 819491 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.5487. Min Act: -0.0000

Data Index: 748511 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.3368. Min Act: -0.0000

Data Index: 215575 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.5719. Min Act: -0.0000

Data Index: 701232 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.5443. Min Act: -0.0000

Data Index: 195386 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 3.5137. Min Range: -3.5137

Max Act: 2.4011. Min Act: -0.0000

Data Index: 1143015 (C4 (Web Text))

Max Activating Token Index: 425