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

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

Neuron 3581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.2115. Min Act: -0.0000

Data Index: 938502 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0171. Min Act: -0.0000

Data Index: 1309949 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.7591. Min Act: -0.0000

Data Index: 928013 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.8560. Min Act: -0.0000

Data Index: 483799 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.6209. Min Act: -0.0000

Data Index: 1322263 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.1634. Min Act: -0.0000

Data Index: 1014904 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.9046. Min Act: -0.0000

Data Index: 1031134 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.8179. Min Act: -0.0000

Data Index: 714208 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.8095. Min Act: -0.0000

Data Index: 44957 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.5653. Min Act: -0.0000

Data Index: 198536 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.6643. Min Act: -0.0000

Data Index: 297541 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.4948. Min Act: -0.0000

Data Index: 634951 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.3075. Min Act: -0.0000

Data Index: 745548 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.2422. Min Act: -0.0000

Data Index: 786435 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.3868. Min Act: -0.0000

Data Index: 1101819 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.3877. Min Act: -0.0000

Data Index: 249331 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.3316. Min Act: -0.0000

Data Index: 369621 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.4956. Min Act: -0.0000

Data Index: 743529 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 4.2115. Min Range: -4.2115

Max Act: 3.2353. Min Act: -0.0000

Data Index: 730545 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 4.2115. Min Range: -4.2115

Max Act: 2.9420. Min Act: -0.0000

Data Index: 352347 (C4 (Web Text))

Max Activating Token Index: 870