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

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

Neuron 2079 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5839. Min Range: -4.5839

Max Act: 4.5839. Min Act: -0.0000

Data Index: 999482 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.2553. Min Act: -0.0000

Data Index: 810665 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.4430. Min Act: -0.0000

Data Index: 933068 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.2566. Min Act: -0.0000

Data Index: 396959 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.0938. Min Act: -0.0000

Data Index: 415155 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.7312. Min Act: -0.0000

Data Index: 80625 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.9523. Min Act: -0.0000

Data Index: 191096 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.9571. Min Act: -0.0000

Data Index: 793397 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.9761. Min Act: -0.0000

Data Index: 930180 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.8161. Min Act: -0.0000

Data Index: 416509 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.9713. Min Act: -0.0000

Data Index: 535202 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.8137. Min Act: -0.0000

Data Index: 719999 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.8107. Min Act: -0.0000

Data Index: 276379 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.0575. Min Act: 0.0000

Data Index: 782771 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.9141. Min Act: -0.0000

Data Index: 692353 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.7177. Min Act: -0.0000

Data Index: 185752 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 4.5839. Min Range: -4.5839

Max Act: 3.2062. Min Act: -0.0000

Data Index: 1082329 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.7652. Min Act: -0.0000

Data Index: 520703 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.6191. Min Act: -0.0000

Data Index: 491548 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 4.5839. Min Range: -4.5839

Max Act: 2.7374. Min Act: -0.0000

Data Index: 957812 (C4 (Web Text))

Max Activating Token Index: 992