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

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

Neuron 187 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.8563. Min Act: -0.0000

Data Index: 265754 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.2956. Min Act: 0.0000

Data Index: 1314349 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.0154. Min Act: -0.0000

Data Index: 196057 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 3.8563. Min Range: -3.8563

Max Act: 3.0025. Min Act: -0.0000

Data Index: 1336222 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.9551. Min Act: -0.0000

Data Index: 579898 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.8801. Min Act: -0.0000

Data Index: 248168 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.7772. Min Act: -0.0000

Data Index: 26734 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.7494. Min Act: 0.0001

Data Index: 611644 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.6010. Min Act: -0.0000

Data Index: 1236401 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5904. Min Act: -0.0000

Data Index: 104000 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5487. Min Act: -0.0000

Data Index: 366528 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5535. Min Act: -0.0000

Data Index: 1542101 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.6701. Min Act: -0.0000

Data Index: 275161 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5617. Min Act: -0.0000

Data Index: 1593221 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5122. Min Act: -0.0000

Data Index: 1603887 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.4962. Min Act: -0.0000

Data Index: 1455904 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.5119. Min Act: 0.0000

Data Index: 1085315 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.4842. Min Act: -0.0000

Data Index: 1646592 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.4701. Min Act: -0.0000

Data Index: 1040486 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.8563. Min Range: -3.8563

Max Act: 2.4512. Min Act: -0.0000

Data Index: 1369380 (Python Code)

Max Activating Token Index: 971