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

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

Neuron 1450 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0000

Data Index: 408494 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5934. Min Act: -0.0000

Data Index: 895535 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5800. Min Act: -0.0000

Data Index: 356123 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5462. Min Act: -0.0000

Data Index: 744231 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1055874 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4929. Min Act: -0.0000

Data Index: 329451 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4851. Min Act: -0.0000

Data Index: 995312 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5035. Min Act: -0.0000

Data Index: 815007 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4595. Min Act: -0.0000

Data Index: 540471 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4646. Min Act: -0.0000

Data Index: 159740 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4569. Min Act: -0.0000

Data Index: 903212 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4717. Min Act: -0.0000

Data Index: 482424 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4673. Min Act: -0.0000

Data Index: 836190 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4609. Min Act: -0.0000

Data Index: 911276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4431. Min Act: -0.0000

Data Index: 2257 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4460. Min Act: -0.0000

Data Index: 638020 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4525. Min Act: -0.0000

Data Index: 448283 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1054649 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4270. Min Act: -0.0000

Data Index: 201152 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1068979 (C4 (Web Text))

Max Activating Token Index: 670