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

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

Neuron 1356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8610. Min Act: -0.0001

Data Index: 362351 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8648. Min Act: -0.0001

Data Index: 200704 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0001

Data Index: 771053 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8534. Min Act: -0.0002

Data Index: 553270 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8131. Min Act: -0.0002

Data Index: 866753 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7979. Min Act: -0.0001

Data Index: 280020 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7875. Min Act: -0.0002

Data Index: 654222 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7599. Min Act: -0.0002

Data Index: 92299 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7785. Min Act: -0.0001

Data Index: 599066 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7654. Min Act: -0.0002

Data Index: 1230850 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7889. Min Act: -0.0002

Data Index: 488347 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7416. Min Act: -0.0002

Data Index: 639210 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7554. Min Act: -0.0001

Data Index: 760597 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7854. Min Act: -0.0002

Data Index: 122108 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7777. Min Act: -0.0002

Data Index: 318576 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7537. Min Act: -0.0001

Data Index: 1270490 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7303. Min Act: -0.0002

Data Index: 79577 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7319. Min Act: -0.0002

Data Index: 316935 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7762. Min Act: -0.0002

Data Index: 638237 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7321. Min Act: -0.0001

Data Index: 898577 (C4 (Web Text))

Max Activating Token Index: 569