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

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

Neuron 566 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: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0000

Data Index: 980908 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6284. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6020. Min Act: -0.0000

Data Index: 777767 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5647. Min Act: -0.0000

Data Index: 662815 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5811. Min Act: -0.0000

Data Index: 800768 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4968. Min Act: -0.0000

Data Index: 425446 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4653. Min Act: -0.0000

Data Index: 246892 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4682. Min Act: -0.0000

Data Index: 711051 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4435. Min Act: -0.0000

Data Index: 503541 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4262. Min Act: -0.0000

Data Index: 166506 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4233. Min Act: -0.0000

Data Index: 141581 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4090. Min Act: -0.0000

Data Index: 161658 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4188. Min Act: -0.0000

Data Index: 727559 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4519. Min Act: -0.0000

Data Index: 565666 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.3770. Min Act: -0.0000

Data Index: 198453 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.3905. Min Act: -0.0000

Data Index: 92633 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1225905 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4150. Min Act: -0.0000

Data Index: 138022 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1305020 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.4192. Min Act: -0.0000

Data Index: 65746 (C4 (Web Text))

Max Activating Token Index: 357