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

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

Neuron 4782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.9883. Min Act: -0.0000

Data Index: 926252 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.4949. Min Act: -0.0000

Data Index: 616167 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.5179. Min Act: -0.0000

Data Index: 266049 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.0730. Min Act: -0.0000

Data Index: 493812 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.3006. Min Act: -0.0000

Data Index: 1231714 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.2799. Min Act: -0.0000

Data Index: 941434 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.8983. Min Act: -0.0000

Data Index: 242575 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.0064. Min Act: -0.0000

Data Index: 29368 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.0303. Min Act: -0.0000

Data Index: 1030642 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 4.9883. Min Range: -4.9883

Max Act: 4.0400. Min Act: -0.0000

Data Index: 272765 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.8635. Min Act: -0.0000

Data Index: 1098109 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7271. Min Act: -0.0000

Data Index: 1142762 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.8394. Min Act: -0.0000

Data Index: 554638 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7838. Min Act: -0.0000

Data Index: 1147685 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7481. Min Act: -0.0000

Data Index: 264872 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.5861. Min Act: -0.0000

Data Index: 661769 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7470. Min Act: -0.0000

Data Index: 1301934 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7509. Min Act: -0.0000

Data Index: 559732 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7100. Min Act: -0.0000

Data Index: 1284153 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 4.9883. Min Range: -4.9883

Max Act: 3.7244. Min Act: -0.0000

Data Index: 891669 (C4 (Web Text))

Max Activating Token Index: 757