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

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

Neuron 3031 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.6276. Min Act: -0.0001

Data Index: 1531511 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.4777. Min Act: -0.0001

Data Index: 687759 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.4286. Min Act: -0.0001

Data Index: 1602065 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1301054 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.3156. Min Act: -0.0001

Data Index: 799967 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2980. Min Act: -0.0001

Data Index: 194659 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1144777 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2703. Min Act: -0.0001

Data Index: 589306 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2739. Min Act: -0.0001

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.3280. Min Act: -0.0001

Data Index: 184514 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1336707 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1603247 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1107759 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.3137. Min Act: -0.0001

Data Index: 587660 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2808. Min Act: -0.0001

Data Index: 771853 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1090075 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2424. Min Act: -0.0001

Data Index: 365788 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2415. Min Act: -0.0001

Data Index: 808787 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2590. Min Act: -0.0001

Data Index: 590192 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.6276. Min Range: -0.6276

Max Act: 0.2195. Min Act: -0.0001

Data Index: 334878 (C4 (Web Text))

Max Activating Token Index: 123