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

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

Neuron 4903 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 109335 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1558169 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1585276 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1178447 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 206293 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 520802 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1121990 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1049304 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 681463 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 633499 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 169844 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 837152 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 194664 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1273506 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0138. Min Act: -0.0002

Data Index: 873105 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1634992 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1451188 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0002

Data Index: 886486 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0130. Min Act: -0.0002

Data Index: 895002 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1257137 (C4 (Web Text))

Max Activating Token Index: 381