Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2048 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0001

Data Index: 653406 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1111. Min Act: -0.0001

Data Index: 12111 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1047. Min Act: -0.0001

Data Index: 844126 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1102. Min Act: -0.0001

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1017. Min Act: -0.0001

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0893. Min Act: -0.0001

Data Index: 207867 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1030. Min Act: -0.0001

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0978. Min Act: -0.0001

Data Index: 464268 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1003. Min Act: -0.0001

Data Index: 334390 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1007. Min Act: -0.0001

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0994. Min Act: -0.0001

Data Index: 248335 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0978. Min Act: -0.0001

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0938. Min Act: -0.0001

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1333867 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0968. Min Act: -0.0001

Data Index: 746507 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0869. Min Act: -0.0001

Data Index: 927282 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1301612 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0913. Min Act: -0.0001

Data Index: 591932 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1131802 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0929. Min Act: -0.0001

Data Index: 787556 (C4 (Web Text))

Max Activating Token Index: 318