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

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

Neuron 208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6027. Min Range: -2.6027

Max Act: 2.6027. Min Act: -0.0001

Data Index: 836417 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 2.6027. Min Range: -2.6027

Max Act: 2.5645. Min Act: -0.0001

Data Index: 424835 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.6027. Min Range: -2.6027

Max Act: 2.2410. Min Act: -0.0001

Data Index: 947295 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.8304. Min Act: -0.0000

Data Index: 50300 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.7180. Min Act: -0.0001

Data Index: 104658 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1344514 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.7881. Min Act: -0.0001

Data Index: 1022462 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.6312. Min Act: -0.0000

Data Index: 246546 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5551. Min Act: -0.0000

Data Index: 239594 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.7748. Min Act: -0.0000

Data Index: 300916 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5977. Min Act: -0.0000

Data Index: 492125 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5614. Min Act: -0.0000

Data Index: 97497 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5122. Min Act: -0.0000

Data Index: 194476 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.4567. Min Act: -0.0001

Data Index: 7814 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.6016. Min Act: -0.0000

Data Index: 448567 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5747. Min Act: -0.0001

Data Index: 820396 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1250281 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1153979 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.4282. Min Act: -0.0000

Data Index: 693293 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.6027. Min Range: -2.6027

Max Act: 1.4326. Min Act: -0.0001

Data Index: 650799 (C4 (Web Text))

Max Activating Token Index: 317