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

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

Neuron 4089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1105. Min Range: -3.1105

Max Act: 3.1105. Min Act: -0.0000

Data Index: 241097 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 3.1105. Min Range: -3.1105

Max Act: 2.4006. Min Act: -0.0000

Data Index: 287161 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 3.1105. Min Range: -3.1105

Max Act: 2.6275. Min Act: -0.0000

Data Index: 714324 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 3.1105. Min Range: -3.1105

Max Act: 2.4778. Min Act: -0.0000

Data Index: 91542 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.1105. Min Range: -3.1105

Max Act: 2.2090. Min Act: -0.0000

Data Index: 439642 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.7081. Min Act: -0.0000

Data Index: 553564 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.8026. Min Act: -0.0000

Data Index: 587825 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.5972. Min Act: -0.0000

Data Index: 986382 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.6743. Min Act: -0.0000

Data Index: 45026 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.7317. Min Act: -0.0000

Data Index: 93399 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.5865. Min Act: -0.0000

Data Index: 39426 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.6085. Min Act: -0.0000

Data Index: 942453 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.4368. Min Act: -0.0000

Data Index: 109408 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.3811. Min Act: -0.0000

Data Index: 304980 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.3435. Min Act: -0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.3072. Min Act: -0.0000

Data Index: 250301 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.2224. Min Act: 0.0000

Data Index: 743564 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.1964. Min Act: -0.0000

Data Index: 358636 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.1963. Min Act: -0.0000

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.1105. Min Range: -3.1105

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1083321 (C4 (Web Text))

Max Activating Token Index: 742