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

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

Neuron 4118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0801. Min Act: -0.0000

Data Index: 920065 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9811. Min Act: -0.0000

Data Index: 967467 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9511. Min Act: -0.0000

Data Index: 187242 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9669. Min Act: -0.0000

Data Index: 906942 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9424. Min Act: -0.0000

Data Index: 944656 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9344. Min Act: -0.0000

Data Index: 296461 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8758. Min Act: -0.0000

Data Index: 755878 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9002. Min Act: -0.0000

Data Index: 733942 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8602. Min Act: -0.0000

Data Index: 776463 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8581. Min Act: -0.0000

Data Index: 253687 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8369. Min Act: -0.0000

Data Index: 604599 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8512. Min Act: -0.0000

Data Index: 191825 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1240275 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8018. Min Act: -0.0000

Data Index: 767301 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7853. Min Act: -0.0000

Data Index: 157501 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7556. Min Act: -0.0000

Data Index: 839149 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8085. Min Act: -0.0000

Data Index: 36784 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1098231 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7595. Min Act: -0.0000

Data Index: 672711 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7451. Min Act: -0.0000

Data Index: 438023 (C4 (Web Text))

Max Activating Token Index: 839