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

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

Neuron 1996 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: 2.0333. Min Range: -2.0333

Max Act: 2.0247. Min Act: -0.0000

Data Index: 238834 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 2.0333. Min Range: -2.0333

Max Act: 2.0333. Min Act: -0.0000

Data Index: 1046474 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.9846. Min Act: -0.0000

Data Index: 950456 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.5964. Min Act: -0.0000

Data Index: 1261603 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.5307. Min Act: -0.0000

Data Index: 379152 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.5033. Min Act: -0.0000

Data Index: 39517 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.5536. Min Act: -0.0000

Data Index: 822509 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4934. Min Act: -0.0000

Data Index: 1358493 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4050. Min Act: -0.0000

Data Index: 595078 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.5009. Min Act: -0.0000

Data Index: 377058 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4986. Min Act: -0.0000

Data Index: 881575 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4853. Min Act: -0.0000

Data Index: 669467 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4300. Min Act: -0.0000

Data Index: 877331 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.3931. Min Act: -0.0000

Data Index: 567820 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.2629. Min Act: -0.0000

Data Index: 21791 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.3842. Min Act: -0.0000

Data Index: 502156 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.4310. Min Act: -0.0000

Data Index: 247129 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1133527 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1211756 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.0333. Min Range: -2.0333

Max Act: 1.3421. Min Act: -0.0000

Data Index: 359357 (C4 (Web Text))

Max Activating Token Index: 716