Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 789 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4394. Min Act: -0.0001

Data Index: 34197 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4806. Min Act: -0.0001

Data Index: 1061093 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4533. Min Act: -0.0001

Data Index: 157572 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4289. Min Act: -0.0001

Data Index: 1242312 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3969. Min Act: -0.0001

Data Index: 323244 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4287. Min Act: -0.0001

Data Index: 1270509 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4074. Min Act: -0.0001

Data Index: 661255 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1312978 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3804. Min Act: -0.0001

Data Index: 1329116 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1142531 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1106055 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4020. Min Act: -0.0001

Data Index: 615925 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3884. Min Act: -0.0001

Data Index: 105418 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3780. Min Act: -0.0001

Data Index: 64139 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3370. Min Act: -0.0001

Data Index: 66003 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3846. Min Act: -0.0001

Data Index: 374059 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3822. Min Act: -0.0001

Data Index: 270525 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3481. Min Act: -0.0001

Data Index: 829349 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3570. Min Act: -0.0001

Data Index: 480641 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3336. Min Act: -0.0001

Data Index: 486287 (C4 (Web Text))

Max Activating Token Index: 71