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

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

Neuron 421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1072. Min Act: -0.0003

Data Index: 83582 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0003

Data Index: 869167 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1060. Min Act: -0.0003

Data Index: 402820 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0998. Min Act: -0.0003

Data Index: 195857 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0971. Min Act: -0.0003

Data Index: 624164 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0941. Min Act: -0.0004

Data Index: 1285118 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0963. Min Act: -0.0004

Data Index: 33658 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0948. Min Act: -0.0003

Data Index: 516844 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0945. Min Act: -0.0003

Data Index: 892603 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0984. Min Act: -0.0003

Data Index: 1014394 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0933. Min Act: -0.0003

Data Index: 482508 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0957. Min Act: -0.0003

Data Index: 605097 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0959. Min Act: -0.0003

Data Index: 279624 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0946. Min Act: -0.0003

Data Index: 813805 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0958. Min Act: -0.0003

Data Index: 197319 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0928. Min Act: -0.0004

Data Index: 194937 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0961. Min Act: -0.0003

Data Index: 1017568 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0917. Min Act: -0.0003

Data Index: 1335110 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0965. Min Act: -0.0003

Data Index: 737215 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0920. Min Act: -0.0004

Data Index: 385335 (C4 (Web Text))

Max Activating Token Index: 412