Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1687. Min Act: -0.0001

Data Index: 925090 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.6034. Min Act: -0.0001

Data Index: 554681 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.5204. Min Act: -0.0000

Data Index: 963707 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.5076. Min Act: -0.0001

Data Index: 1082631 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.4899. Min Act: -0.0000

Data Index: 272033 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1084473 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.4308. Min Act: -0.0000

Data Index: 222947 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.1874. Min Act: -0.0000

Data Index: 497390 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.4113. Min Act: -0.0001

Data Index: 701222 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1197354 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3007. Min Act: -0.0000

Data Index: 992764 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3276. Min Act: -0.0000

Data Index: 685245 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.2816. Min Act: -0.0000

Data Index: 253021 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.2812. Min Act: -0.0000

Data Index: 634390 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1310691 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1088400 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.2707. Min Act: -0.0000

Data Index: 334272 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3860. Min Act: -0.0001

Data Index: 1065567 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.3386. Min Act: -0.0001

Data Index: 793828 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1041859 (C4 (Web Text))

Max Activating Token Index: 621