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

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

Neuron 1610 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: 0.3646. Min Range: -0.3646

Max Act: 0.3646. Min Act: -0.0001

Data Index: 1047734 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3505. Min Act: -0.0001

Data Index: 88422 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3290. Min Act: -0.0001

Data Index: 576998 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3274. Min Act: -0.0001

Data Index: 643910 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3008. Min Act: -0.0001

Data Index: 264600 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3122. Min Act: -0.0001

Data Index: 610795 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3196. Min Act: -0.0001

Data Index: 99274 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2917. Min Act: -0.0001

Data Index: 977010 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1157830 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3076. Min Act: -0.0001

Data Index: 710595 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2974. Min Act: -0.0001

Data Index: 673574 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2953. Min Act: -0.0001

Data Index: 255486 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1056136 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2956. Min Act: -0.0001

Data Index: 995471 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1214797 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3151. Min Act: -0.0001

Data Index: 102586 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2926. Min Act: -0.0001

Data Index: 97517 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2819. Min Act: -0.0001

Data Index: 795226 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2926. Min Act: -0.0001

Data Index: 231014 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2920. Min Act: -0.0001

Data Index: 386115 (C4 (Web Text))

Max Activating Token Index: 479