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

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

Neuron 4186 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: 1.2173. Min Range: -1.2173

Max Act: 1.2173. Min Act: 0.0000

Data Index: 963056 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9826. Min Act: -0.0000

Data Index: 476236 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9988. Min Act: 0.0001

Data Index: 1035067 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9623. Min Act: -0.0000

Data Index: 427466 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9383. Min Act: 0.0000

Data Index: 795838 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9653. Min Act: -0.0000

Data Index: 110518 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9518. Min Act: 0.0001

Data Index: 990280 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8643. Min Act: 0.0000

Data Index: 1212547 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1276940 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8040. Min Act: -0.0000

Data Index: 813589 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8656. Min Act: -0.0000

Data Index: 110845 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8374. Min Act: 0.0001

Data Index: 1129884 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8886. Min Act: -0.0000

Data Index: 161065 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1054615 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8766. Min Act: 0.0000

Data Index: 174301 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8170. Min Act: -0.0000

Data Index: 64498 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7362. Min Act: 0.0001

Data Index: 1120667 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7755. Min Act: -0.0000

Data Index: 197402 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7291. Min Act: -0.0000

Data Index: 448126 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7434. Min Act: 0.0001

Data Index: 1084692 (C4 (Web Text))

Max Activating Token Index: 38