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

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

Neuron 143 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: 0.5070. Min Range: -0.5070

Max Act: 0.5070. Min Act: -0.0001

Data Index: 1296131 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4525. Min Act: -0.0001

Data Index: 687580 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4195. Min Act: -0.0001

Data Index: 246495 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4488. Min Act: -0.0001

Data Index: 967400 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4305. Min Act: -0.0001

Data Index: 192030 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4026. Min Act: -0.0001

Data Index: 1187724 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4282. Min Act: -0.0001

Data Index: 378555 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1066295 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4555. Min Act: -0.0001

Data Index: 809869 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4016. Min Act: -0.0001

Data Index: 737544 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3693. Min Act: -0.0001

Data Index: 653592 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1359416 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3629. Min Act: -0.0001

Data Index: 768843 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3665. Min Act: -0.0001

Data Index: 473360 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3595. Min Act: -0.0001

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1343957 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3781. Min Act: -0.0001

Data Index: 755044 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3394. Min Act: -0.0001

Data Index: 751489 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3668. Min Act: -0.0001

Data Index: 685099 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3341. Min Act: -0.0001

Data Index: 657065 (C4 (Web Text))

Max Activating Token Index: 335