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

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

Neuron 2716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1102748 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0988. Min Act: -0.0002

Data Index: 806534 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0951. Min Act: -0.0002

Data Index: 38921 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0895. Min Act: -0.0002

Data Index: 197450 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0893. Min Act: -0.0002

Data Index: 151599 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0897. Min Act: -0.0002

Data Index: 233148 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0935. Min Act: -0.0002

Data Index: 888786 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0910. Min Act: -0.0002

Data Index: 881458 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0965. Min Act: -0.0002

Data Index: 474606 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1174811 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0934. Min Act: -0.0002

Data Index: 757178 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0895. Min Act: -0.0002

Data Index: 457160 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0893. Min Act: -0.0002

Data Index: 974280 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0847. Min Act: -0.0002

Data Index: 366991 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0822. Min Act: -0.0002

Data Index: 341620 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0818. Min Act: -0.0002

Data Index: 518582 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1199247 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0815. Min Act: -0.0002

Data Index: 894459 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0730. Min Act: -0.0002

Data Index: 261537 (C4 (Web Text))

Max Activating Token Index: 371