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

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

Neuron 1123 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: 1.8940. Min Range: -1.8940

Max Act: 1.8940. Min Act: -0.0000

Data Index: 1304557 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.2532. Min Act: -0.0000

Data Index: 197477 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.8940. Min Range: -1.8940

Max Act: 1.1284. Min Act: -0.0000

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.9507. Min Act: -0.0000

Data Index: 805580 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8601. Min Act: -0.0000

Data Index: 330225 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.9261. Min Act: -0.0000

Data Index: 38539 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.9054. Min Act: -0.0000

Data Index: 465939 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8902. Min Act: 0.0000

Data Index: 717632 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8627. Min Act: -0.0000

Data Index: 90262 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8627. Min Act: -0.0000

Data Index: 383363 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.9069. Min Act: -0.0000

Data Index: 538022 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8747. Min Act: -0.0000

Data Index: 422260 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.7943. Min Act: 0.0000

Data Index: 856639 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8159. Min Act: -0.0000

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.6714. Min Act: -0.0000

Data Index: 120163 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1210198 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.7996. Min Act: -0.0000

Data Index: 869908 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.8199. Min Act: -0.0000

Data Index: 738005 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.7520. Min Act: -0.0000

Data Index: 864558 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.8940. Min Range: -1.8940

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1128224 (C4 (Web Text))

Max Activating Token Index: 31