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

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

Neuron 2126 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1638972 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1465810 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3124. Min Act: -0.0001

Data Index: 1363668 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3123. Min Act: -0.0001

Data Index: 1506379 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1460560 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1649883 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1488526 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1437264 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1487514 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1481968 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2962. Min Act: -0.0001

Data Index: 263330 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1550821 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1634408 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2890. Min Act: -0.0001

Data Index: 17787 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1438150 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1623117 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1088258 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2726. Min Act: -0.0001

Data Index: 1397517 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1467761 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2691. Min Act: -0.0001

Data Index: 1472712 (Python Code)

Max Activating Token Index: 599