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

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

Neuron 5928 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6681. Min Act: -0.0002

Data Index: 1095904 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6356. Min Act: -0.0002

Data Index: 262417 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6408. Min Act: -0.0002

Data Index: 550114 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6381. Min Act: -0.0002

Data Index: 1245956 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6279. Min Act: -0.0002

Data Index: 119408 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6174. Min Act: -0.0002

Data Index: 771120 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6214. Min Act: -0.0002

Data Index: 515070 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6103. Min Act: -0.0002

Data Index: 1010521 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6052. Min Act: -0.0002

Data Index: 1025906 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6004. Min Act: -0.0002

Data Index: 1150795 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6139. Min Act: -0.0002

Data Index: 429061 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6018. Min Act: -0.0002

Data Index: 1024385 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6024. Min Act: -0.0002

Data Index: 844498 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5994. Min Act: -0.0002

Data Index: 1048283 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6124. Min Act: -0.0002

Data Index: 225395 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5953. Min Act: -0.0002

Data Index: 960013 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6074. Min Act: -0.0002

Data Index: 470288 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5933. Min Act: -0.0002

Data Index: 154743 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6025. Min Act: -0.0002

Data Index: 224220 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5909. Min Act: -0.0002

Data Index: 943946 (C4 (Web Text))

Max Activating Token Index: 682