Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 950 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1170831 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0103. Min Act: -0.0006

Data Index: 194094 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0006

Data Index: 318792 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1290476 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1090856 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0097. Min Act: -0.0006

Data Index: 804431 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1330816 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1121584 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0096. Min Act: -0.0006

Data Index: 842429 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0094. Min Act: -0.0006

Data Index: 854097 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0095. Min Act: -0.0006

Data Index: 614551 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0094. Min Act: -0.0006

Data Index: 582362 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0093. Min Act: -0.0006

Data Index: 42985 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1026976 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1356619 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1235824 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 850578 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 88200 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 275620 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 332428 (C4 (Web Text))

Max Activating Token Index: 342