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

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

Neuron 6014 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7011. Min Range: -4.7011

Max Act: 4.7011. Min Act: -0.0000

Data Index: 463953 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 4.7011. Min Range: -4.7011

Max Act: 4.5579. Min Act: -0.0000

Data Index: 693084 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.6724. Min Act: -0.0001

Data Index: 369239 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.6416. Min Act: -0.0000

Data Index: 380550 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.8562. Min Act: -0.0000

Data Index: 467011 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 4.7011. Min Range: -4.7011

Max Act: 2.9143. Min Act: -0.0000

Data Index: 1271313 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.2720. Min Act: -0.0000

Data Index: 492802 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.6300. Min Act: -0.0001

Data Index: 546744 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.1613. Min Act: -0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.2614. Min Act: -0.0001

Data Index: 318600 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.4043. Min Act: -0.0000

Data Index: 462051 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.2127. Min Act: -0.0000

Data Index: 532833 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.4834. Min Act: -0.0001

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.1940. Min Act: -0.0000

Data Index: 1021617 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.1439. Min Act: -0.0000

Data Index: 107156 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.3662. Min Act: -0.0000

Data Index: 780842 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.2600. Min Act: -0.0001

Data Index: 922870 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.3903. Min Act: -0.0001

Data Index: 1188466 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.0952. Min Act: -0.0001

Data Index: 141657 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 4.7011. Min Range: -4.7011

Max Act: 3.1998. Min Act: -0.0000

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 59