Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 963 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3841. Min Act: -0.0001

Data Index: 168287 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3430. Min Act: -0.0002

Data Index: 1352953 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3330. Min Act: -0.0002

Data Index: 348286 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3254. Min Act: -0.0002

Data Index: 299010 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3256. Min Act: -0.0002

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3224. Min Act: -0.0003

Data Index: 685416 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3183. Min Act: -0.0002

Data Index: 633652 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3284. Min Act: -0.0000

Data Index: 732404 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3134. Min Act: -0.0002

Data Index: 750777 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3121. Min Act: -0.0002

Data Index: 813800 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3026. Min Act: -0.0002

Data Index: 464905 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2969. Min Act: -0.0001

Data Index: 778914 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2967. Min Act: -0.0001

Data Index: 60964 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2944. Min Act: -0.0002

Data Index: 1213122 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2892. Min Act: -0.0002

Data Index: 160636 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2794. Min Act: -0.0002

Data Index: 1346151 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2792. Min Act: -0.0002

Data Index: 1240706 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2782. Min Act: -0.0002

Data Index: 1222681 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2754. Min Act: -0.0002

Data Index: 329565 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2751. Min Act: -0.0002

Data Index: 611899 (C4 (Web Text))

Max Activating Token Index: 196