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

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

Neuron 4997 in Layer 1

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: 2.3233. Min Range: -2.3233

Max Act: 2.3233. Min Act: -0.0002

Data Index: 81851 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 2.3233. Min Range: -2.3233

Max Act: 2.2878. Min Act: -0.0002

Data Index: 883293 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.3233. Min Range: -2.3233

Max Act: 2.0466. Min Act: -0.0003

Data Index: 969827 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 2.3233. Min Range: -2.3233

Max Act: 2.0229. Min Act: -0.0002

Data Index: 821628 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9981. Min Act: -0.0002

Data Index: 1310270 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9890. Min Act: -0.0002

Data Index: 683419 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9601. Min Act: -0.0003

Data Index: 604185 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9522. Min Act: -0.0003

Data Index: 378282 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9115. Min Act: -0.0002

Data Index: 1176462 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9166. Min Act: -0.0002

Data Index: 43604 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9055. Min Act: -0.0002

Data Index: 799069 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.9448. Min Act: -0.0002

Data Index: 1037444 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.8347. Min Act: -0.0002

Data Index: 969034 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.8448. Min Act: -0.0002

Data Index: 786330 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.7925. Min Act: -0.0002

Data Index: 760255 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.7904. Min Act: -0.0002

Data Index: 473967 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.7976. Min Act: -0.0002

Data Index: 1009011 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.8123. Min Act: -0.0002

Data Index: 1108590 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.8223. Min Act: -0.0002

Data Index: 338732 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 2.3233. Min Range: -2.3233

Max Act: 1.7920. Min Act: -0.0002

Data Index: 471786 (C4 (Web Text))

Max Activating Token Index: 817