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

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

Neuron 1054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1813. Min Range: -1.1813

Max Act: 1.1813. Min Act: -0.0001

Data Index: 336947 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.8669. Min Act: -0.0001

Data Index: 310779 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7890. Min Act: -0.0001

Data Index: 129704 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7313. Min Act: -0.0001

Data Index: 553595 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.8002. Min Act: -0.0001

Data Index: 726483 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7395. Min Act: -0.0001

Data Index: 770530 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7804. Min Act: -0.0001

Data Index: 648308 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6617. Min Act: -0.0001

Data Index: 465336 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1208088 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7197. Min Act: -0.0001

Data Index: 96924 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1168057 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6130. Min Act: -0.0001

Data Index: 255198 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7080. Min Act: -0.0001

Data Index: 909092 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6866. Min Act: -0.0001

Data Index: 136409 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6535. Min Act: -0.0001

Data Index: 32196 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6835. Min Act: -0.0001

Data Index: 1329999 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7049. Min Act: -0.0001

Data Index: 970156 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7223. Min Act: -0.0001

Data Index: 553491 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.7232. Min Act: -0.0001

Data Index: 72135 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.1813. Min Range: -1.1813

Max Act: 0.6749. Min Act: -0.0001

Data Index: 861730 (C4 (Web Text))

Max Activating Token Index: 346