Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1483 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4852. Min Act: -0.0000

Data Index: 329163 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.5027. Min Act: -0.0000

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4806. Min Act: -0.0000

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4757. Min Act: -0.0000

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1101097 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4644. Min Act: 0.0000

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4450. Min Act: 0.0000

Data Index: 1118853 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1041875 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4649. Min Act: -0.0000

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1281486 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4387. Min Act: -0.0000

Data Index: 613965 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1042224 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4348. Min Act: -0.0000

Data Index: 509456 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4192. Min Act: -0.0000

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4113. Min Act: 0.0000

Data Index: 1309080 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4347. Min Act: -0.0000

Data Index: 878003 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4323. Min Act: 0.0000

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4213. Min Act: 0.0000

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 82