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

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

Neuron 2454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.5049. Min Act: -0.0000

Data Index: 822425 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1505 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1401761 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3393. Min Act: -0.0000

Data Index: 847891 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1645213 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3482. Min Act: -0.0000

Data Index: 629638 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1453894 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1493573 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1512228 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1526116 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2894. Min Act: -0.0000

Data Index: 113199 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2907. Min Act: -0.0000

Data Index: 468097 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1317409 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1084879 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2896. Min Act: -0.0000

Data Index: 126561 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1430805 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1515781 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1521762 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1377936 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2856. Min Act: -0.0000

Data Index: 805721 (C4 (Web Text))

Max Activating Token Index: 982