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

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

Neuron 4220 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.7516. Min Act: -0.0000

Data Index: 776913 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.6572. Min Act: -0.0000

Data Index: 141352 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1109947 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1325828 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.0283. Min Act: -0.0000

Data Index: 673395 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.9506. Min Act: -0.0000

Data Index: 74387 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.8638. Min Act: -0.0000

Data Index: 158767 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7885. Min Act: -0.0000

Data Index: 231893 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1326550 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.8052. Min Act: -0.0000

Data Index: 635450 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7496. Min Act: -0.0000

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7888. Min Act: -0.0000

Data Index: 994815 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7311. Min Act: -0.0000

Data Index: 673374 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7153. Min Act: -0.0000

Data Index: 167306 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1065774 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1271691 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7362. Min Act: -0.0000

Data Index: 291350 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1307558 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7233. Min Act: -0.0000

Data Index: 780106 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.7516. Min Range: -1.7516

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1032113 (C4 (Web Text))

Max Activating Token Index: 555