Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1522 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4917. Min Act: -0.0001

Data Index: 1541132 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4767. Min Act: -0.0001

Data Index: 771753 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.5015. Min Act: -0.0001

Data Index: 409890 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4182. Min Act: -0.0001

Data Index: 981275 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4440. Min Act: -0.0001

Data Index: 603487 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1086670 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1155974 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4411. Min Act: -0.0001

Data Index: 994244 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4160. Min Act: -0.0001

Data Index: 337993 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4160. Min Act: -0.0001

Data Index: 815279 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4126. Min Act: -0.0001

Data Index: 855461 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4552. Min Act: -0.0001

Data Index: 628820 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4176. Min Act: -0.0001

Data Index: 693114 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1524110 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4285. Min Act: -0.0001

Data Index: 482534 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4164. Min Act: -0.0001

Data Index: 639367 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1044092 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4167. Min Act: -0.0001

Data Index: 1451900 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1380509 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1475563 (Python Code)

Max Activating Token Index: 229