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

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

Neuron 1876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1317156 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1020277 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6786. Min Act: -0.0000

Data Index: 18577 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6312. Min Act: -0.0000

Data Index: 196291 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1312422 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5590. Min Act: -0.0001

Data Index: 1340083 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5244. Min Act: -0.0000

Data Index: 367423 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1320639 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5297. Min Act: -0.0001

Data Index: 286551 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5035. Min Act: -0.0000

Data Index: 669435 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4824. Min Act: -0.0001

Data Index: 251359 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5046. Min Act: -0.0001

Data Index: 476414 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1112606 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5450. Min Act: -0.0001

Data Index: 1057788 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4891. Min Act: -0.0001

Data Index: 917549 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1142095 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4710. Min Act: -0.0000

Data Index: 70731 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4608. Min Act: -0.0001

Data Index: 1302049 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4844. Min Act: -0.0000

Data Index: 974249 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4532. Min Act: -0.0001

Data Index: 933740 (C4 (Web Text))

Max Activating Token Index: 1021