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

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

Neuron 2761 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1161141 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.4813. Min Act: 0.0000

Data Index: 675123 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.4030. Min Act: -0.0001

Data Index: 749327 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2804. Min Act: -0.0000

Data Index: 135954 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.3459. Min Act: -0.0001

Data Index: 1311915 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.2595. Min Act: 0.0001

Data Index: 774014 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1599. Min Act: -0.0000

Data Index: 135790 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1864. Min Act: -0.0000

Data Index: 183378 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1576. Min Act: 0.0000

Data Index: 442066 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0670. Min Act: 0.0000

Data Index: 274178 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.1096. Min Act: -0.0000

Data Index: 981717 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0684. Min Act: 0.0001

Data Index: 1152702 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0913. Min Act: -0.0000

Data Index: 588374 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0451. Min Act: 0.0001

Data Index: 1212463 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0367. Min Act: 0.0001

Data Index: 46369 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.5048. Min Range: -1.5048

Max Act: 0.9997. Min Act: 0.0001

Data Index: 603376 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.5048. Min Range: -1.5048

Max Act: 0.9641. Min Act: 0.0001

Data Index: 741439 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.5048. Min Range: -1.5048

Max Act: 0.9781. Min Act: 0.0000

Data Index: 1132546 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 1.5048. Min Range: -1.5048

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1187582 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.5048. Min Range: -1.5048

Max Act: 0.9802. Min Act: 0.0001

Data Index: 1173236 (C4 (Web Text))

Max Activating Token Index: 576