Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.4622. Min Act: -0.0001

Data Index: 13789 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.4893. Min Act: -0.0001

Data Index: 227015 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3639. Min Act: -0.0001

Data Index: 32393 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.5007. Min Act: -0.0001

Data Index: 1270510 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.2947. Min Act: -0.0001

Data Index: 868467 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3940. Min Act: -0.0001

Data Index: 78061 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.2581. Min Act: -0.0000

Data Index: 159860 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.4684. Min Act: -0.0001

Data Index: 293918 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1514. Min Act: -0.0001

Data Index: 1071487 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1631. Min Act: -0.0001

Data Index: 905352 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.2260. Min Act: -0.0000

Data Index: 641357 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1253. Min Act: -0.0001

Data Index: 211425 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.5007. Min Range: -3.5007

Max Act: 2.9548. Min Act: -0.0000

Data Index: 1125704 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3684. Min Act: -0.0001

Data Index: 1051283 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1007. Min Act: -0.0000

Data Index: 25847 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.0958. Min Act: -0.0000

Data Index: 1106205 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3084. Min Act: -0.0000

Data Index: 667284 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1665. Min Act: -0.0001

Data Index: 1082938 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.1455. Min Act: -0.0001

Data Index: 681272 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 3.5007. Min Range: -3.5007

Max Act: 2.9054. Min Act: -0.0000

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 976