Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5596. Min Act: -0.0000

Data Index: 177186 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5583. Min Act: -0.0000

Data Index: 79259 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4770. Min Act: -0.0000

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4063. Min Act: -0.0000

Data Index: 820147 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1020161 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3803. Min Act: -0.0000

Data Index: 393129 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3813. Min Act: -0.0000

Data Index: 61504 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1342641 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3462. Min Act: -0.0000

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3485. Min Act: -0.0000

Data Index: 333630 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3240. Min Act: -0.0000

Data Index: 617818 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3295. Min Act: -0.0000

Data Index: 109132 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3151. Min Act: -0.0000

Data Index: 236156 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3045. Min Act: -0.0000

Data Index: 623081 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.2937. Min Act: -0.0000

Data Index: 754022 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.2995. Min Act: -0.0000

Data Index: 901488 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1219411 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1345081 (C4 (Web Text))

Max Activating Token Index: 859