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

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

Neuron 3443 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: 0.5333. Min Range: -0.5333

Max Act: 0.5333. Min Act: -0.0000

Data Index: 252036 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1095151 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1161263 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1199077 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.3161. Min Act: -0.0000

Data Index: 482618 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2970. Min Act: -0.0000

Data Index: 547333 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.3145. Min Act: -0.0000

Data Index: 70612 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2965. Min Act: -0.0000

Data Index: 826961 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1205174 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2524. Min Act: -0.0000

Data Index: 832760 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2637. Min Act: -0.0000

Data Index: 857406 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1013942 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1576639 (Python Code)

Max Activating Token Index: 670

Text #13

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2865. Min Act: -0.0000

Data Index: 197188 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2768. Min Act: -0.0000

Data Index: 634590 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2646. Min Act: -0.0000

Data Index: 64142 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2596. Min Act: -0.0000

Data Index: 19374 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1572997 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1328689 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.5333. Min Range: -0.5333

Max Act: 0.2645. Min Act: -0.0000

Data Index: 273763 (C4 (Web Text))

Max Activating Token Index: 39