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

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

Neuron 5145 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7649. Min Act: -0.0001

Data Index: 476926 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7630. Min Act: -0.0001

Data Index: 169613 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7366. Min Act: -0.0001

Data Index: 472787 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7366. Min Act: -0.0001

Data Index: 563274 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7366. Min Act: -0.0001

Data Index: 60095 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1196427 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7294. Min Act: -0.0001

Data Index: 320794 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7266. Min Act: -0.0001

Data Index: 422544 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7090. Min Act: -0.0001

Data Index: 4339 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7157. Min Act: -0.0001

Data Index: 225047 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7000. Min Act: -0.0001

Data Index: 227542 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6897. Min Act: -0.0001

Data Index: 98521 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6885. Min Act: -0.0001

Data Index: 227589 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6897. Min Act: -0.0001

Data Index: 798471 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6939. Min Act: -0.0001

Data Index: 974736 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6790. Min Act: -0.0001

Data Index: 848444 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1637 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6856. Min Act: -0.0001

Data Index: 364341 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6788. Min Act: -0.0001

Data Index: 572092 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6696. Min Act: -0.0001

Data Index: 959472 (C4 (Web Text))

Max Activating Token Index: 63