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

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

Neuron 1029 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5042. Min Range: -2.5042

Max Act: 2.5042. Min Act: -0.0000

Data Index: 1544855 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 2.5042. Min Range: -2.5042

Max Act: 2.3347. Min Act: -0.0000

Data Index: 1392580 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 2.5042. Min Range: -2.5042

Max Act: 2.4608. Min Act: -0.0000

Data Index: 1430468 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 2.5042. Min Range: -2.5042

Max Act: 2.1849. Min Act: -0.0000

Data Index: 1537473 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 2.5042. Min Range: -2.5042

Max Act: 2.1343. Min Act: -0.0000

Data Index: 1542308 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.8167. Min Act: -0.0000

Data Index: 810500 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1037928 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6452. Min Act: -0.0000

Data Index: 264503 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6562. Min Act: -0.0000

Data Index: 728521 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1245816 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1464366 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1181591 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.5575. Min Act: -0.0000

Data Index: 899430 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1111276 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.5851. Min Act: -0.0000

Data Index: 310373 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.4593. Min Act: -0.0000

Data Index: 602040 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.6039. Min Act: -0.0000

Data Index: 197662 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.4652. Min Act: -0.0000

Data Index: 947266 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.4958. Min Act: -0.0000

Data Index: 829864 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.5042. Min Range: -2.5042

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1292559 (C4 (Web Text))

Max Activating Token Index: 450