Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4970. Min Act: -0.0000

Data Index: 985785 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4534. Min Act: -0.0001

Data Index: 953356 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4105. Min Act: -0.0000

Data Index: 782945 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4229. Min Act: -0.0001

Data Index: 703954 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4244. Min Act: -0.0000

Data Index: 429999 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1121902 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3633. Min Act: -0.0001

Data Index: 1046144 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4004. Min Act: -0.0001

Data Index: 133366 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3917. Min Act: -0.0000

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3880. Min Act: -0.0000

Data Index: 747096 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3837. Min Act: -0.0000

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3991. Min Act: -0.0001

Data Index: 1331282 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3816. Min Act: -0.0001

Data Index: 944476 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3782. Min Act: -0.0000

Data Index: 177872 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3502. Min Act: -0.0001

Data Index: 380120 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3626. Min Act: -0.0001

Data Index: 696562 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3742. Min Act: -0.0001

Data Index: 792594 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3994. Min Act: -0.0001

Data Index: 69371 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3584. Min Act: -0.0000

Data Index: 451230 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.3819. Min Act: -0.0000

Data Index: 848869 (C4 (Web Text))

Max Activating Token Index: 733