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

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

Neuron 3016 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.8580. Min Act: -0.0001

Data Index: 441789 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.9005. Min Act: -0.0000

Data Index: 1228527 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.3207. Min Act: -0.0000

Data Index: 889068 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.3117. Min Act: -0.0001

Data Index: 17007 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.2719. Min Act: -0.0001

Data Index: 486712 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0787. Min Act: -0.0001

Data Index: 920076 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.1533. Min Act: -0.0000

Data Index: 1034751 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.1261. Min Act: -0.0001

Data Index: 1108971 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.1165. Min Act: -0.0001

Data Index: 66212 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0815. Min Act: -0.0000

Data Index: 672431 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.7759. Min Act: -0.0001

Data Index: 1652179 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0704. Min Act: -0.0000

Data Index: 263673 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.1976. Min Act: -0.0000

Data Index: 891296 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9583. Min Act: -0.0001

Data Index: 1190533 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0352. Min Act: -0.0000

Data Index: 152740 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0557. Min Act: -0.0001

Data Index: 1319950 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0900. Min Act: -0.0000

Data Index: 214694 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9983. Min Act: -0.0001

Data Index: 1059800 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9930. Min Act: -0.0000

Data Index: 684157 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.7968. Min Act: -0.0000

Data Index: 900284 (C4 (Web Text))

Max Activating Token Index: 460