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

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

Neuron 3643 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: 1.6823. Min Range: -1.6823

Max Act: 1.6823. Min Act: -0.0000

Data Index: 1040736 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5077. Min Act: -0.0000

Data Index: 756488 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1253171 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.6100. Min Act: -0.0000

Data Index: 507412 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5823. Min Act: -0.0000

Data Index: 741191 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1258640 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5320. Min Act: -0.0000

Data Index: 721286 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5070. Min Act: -0.0000

Data Index: 344372 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.5141. Min Act: -0.0000

Data Index: 35210 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1114660 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4670. Min Act: -0.0000

Data Index: 833505 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4565. Min Act: -0.0000

Data Index: 149708 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4410. Min Act: -0.0000

Data Index: 136004 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3790. Min Act: -0.0000

Data Index: 74583 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3548. Min Act: -0.0000

Data Index: 98398 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1070733 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.3527. Min Act: -0.0000

Data Index: 480940 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.4135. Min Act: -0.0000

Data Index: 262670 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.2761. Min Act: -0.0000

Data Index: 425822 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.6823. Min Range: -1.6823

Max Act: 1.2386. Min Act: -0.0000

Data Index: 351994 (C4 (Web Text))

Max Activating Token Index: 263