Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3968 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.6167. Min Act: -0.0000

Data Index: 361010 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.5957. Min Act: -0.0000

Data Index: 248135 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.6405. Min Act: -0.0000

Data Index: 260109 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.3832. Min Act: -0.0000

Data Index: 545070 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1089707 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.5871. Min Act: -0.0000

Data Index: 26602 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.4386. Min Act: -0.0000

Data Index: 534276 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.4543. Min Act: -0.0000

Data Index: 925660 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1180733 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.5017. Min Act: -0.0000

Data Index: 261241 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.3074. Min Act: -0.0000

Data Index: 210676 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.3489. Min Act: -0.0000

Data Index: 224361 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2031. Min Act: -0.0000

Data Index: 294275 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2801. Min Act: -0.0000

Data Index: 160518 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2346. Min Act: -0.0000

Data Index: 480224 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2703. Min Act: -0.0000

Data Index: 461246 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.4280. Min Act: -0.0000

Data Index: 14598 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1000883 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2430. Min Act: -0.0000

Data Index: 691600 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.6405. Min Range: -1.6405

Max Act: 1.2087. Min Act: -0.0000

Data Index: 994423 (C4 (Web Text))

Max Activating Token Index: 604