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

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

Neuron 5064 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1466145 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1472807 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3803. Min Act: -0.0000

Data Index: 651766 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1555898 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1006391 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1617410 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3288. Min Act: -0.0000

Data Index: 834579 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1480709 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1639983 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1262000 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1569273 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1536903 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1577164 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1397158 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1601762 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1520409 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1606585 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1459386 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1438558 (Python Code)

Max Activating Token Index: 872