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

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

Neuron 3185 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.8980. Min Act: -0.0001

Data Index: 64602 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7806. Min Act: -0.0001

Data Index: 895606 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1272776 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7760. Min Act: -0.0001

Data Index: 392737 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7271. Min Act: -0.0001

Data Index: 126750 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1326024 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7305. Min Act: -0.0001

Data Index: 299059 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6661. Min Act: -0.0001

Data Index: 241521 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7019. Min Act: -0.0001

Data Index: 862162 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6778. Min Act: -0.0001

Data Index: 822809 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6825. Min Act: -0.0001

Data Index: 1085579 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6663. Min Act: -0.0001

Data Index: 827070 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6698. Min Act: -0.0001

Data Index: 443649 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6454. Min Act: -0.0001

Data Index: 54753 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1067620 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6372. Min Act: -0.0001

Data Index: 70206 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1139649 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6088. Min Act: -0.0001

Data Index: 1167915 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6162. Min Act: -0.0001

Data Index: 590481 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1010939 (C4 (Web Text))

Max Activating Token Index: 625