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

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

Neuron 3544 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: 2.3997. Min Range: -2.3997

Max Act: 2.3997. Min Act: -0.0002

Data Index: 1071783 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.3997. Min Range: -2.3997

Max Act: 2.0836. Min Act: -0.0002

Data Index: 583148 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.9979. Min Act: -0.0002

Data Index: 292338 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.9881. Min Act: -0.0002

Data Index: 778813 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.9239. Min Act: -0.0002

Data Index: 604393 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.9181. Min Act: -0.0002

Data Index: 995291 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.8845. Min Act: -0.0002

Data Index: 1155087 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.8887. Min Act: -0.0003

Data Index: 1039260 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.8685. Min Act: -0.0002

Data Index: 158585 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.8319. Min Act: -0.0003

Data Index: 390122 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7824. Min Act: -0.0002

Data Index: 528403 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7811. Min Act: -0.0002

Data Index: 829941 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7536. Min Act: -0.0002

Data Index: 825435 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.8030. Min Act: -0.0002

Data Index: 703818 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7589. Min Act: -0.0002

Data Index: 455014 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7503. Min Act: -0.0002

Data Index: 4087 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.6887. Min Act: -0.0002

Data Index: 1187125 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.6990. Min Act: -0.0002

Data Index: 1188804 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7175. Min Act: -0.0002

Data Index: 1188541 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 2.3997. Min Range: -2.3997

Max Act: 1.7372. Min Act: -0.0003

Data Index: 58628 (C4 (Web Text))

Max Activating Token Index: 552