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

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

Neuron 3693 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.8802. Min Act: -0.0000

Data Index: 1372436 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.5083. Min Act: -0.0000

Data Index: 920800 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.6000. Min Act: -0.0000

Data Index: 306080 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9777. Min Act: -0.0000

Data Index: 335130 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.2288. Min Act: -0.0000

Data Index: 549908 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9672. Min Act: -0.0000

Data Index: 749680 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.1022. Min Act: -0.0000

Data Index: 423358 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.0461. Min Act: -0.0000

Data Index: 130887 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.0500. Min Act: -0.0000

Data Index: 1173674 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.1701. Min Act: -0.0000

Data Index: 819965 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 3.8802. Min Range: -3.8802

Max Act: 3.0080. Min Act: -0.0000

Data Index: 505849 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9909. Min Act: -0.0000

Data Index: 1199556 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.6979. Min Act: -0.0000

Data Index: 1181593 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9811. Min Act: -0.0000

Data Index: 486586 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9467. Min Act: -0.0000

Data Index: 238661 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.7866. Min Act: -0.0000

Data Index: 839199 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.9083. Min Act: -0.0000

Data Index: 248515 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.8922. Min Act: -0.0000

Data Index: 689569 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.6234. Min Act: -0.0000

Data Index: 1120095 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 3.8802. Min Range: -3.8802

Max Act: 2.5992. Min Act: -0.0000

Data Index: 741516 (C4 (Web Text))

Max Activating Token Index: 417