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

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

Neuron 2149 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: 4.6552. Min Range: -4.6552

Max Act: 4.3175. Min Act: -0.0000

Data Index: 354069 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.4493. Min Act: -0.0000

Data Index: 54592 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.2910. Min Act: -0.0000

Data Index: 687694 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.6552. Min Act: -0.0000

Data Index: 442861 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.4473. Min Act: -0.0000

Data Index: 667459 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.3086. Min Act: -0.0000

Data Index: 803651 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1148. Min Act: -0.0000

Data Index: 279701 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.2820. Min Act: -0.0000

Data Index: 311769 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 4.6552. Min Range: -4.6552

Max Act: 3.9705. Min Act: -0.0000

Data Index: 78521 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1259. Min Act: -0.0000

Data Index: 239328 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1249. Min Act: -0.0000

Data Index: 1139500 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.2957. Min Act: -0.0000

Data Index: 260038 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1294. Min Act: -0.0000

Data Index: 817906 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.3102. Min Act: -0.0000

Data Index: 42549 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 4.6552. Min Range: -4.6552

Max Act: 3.9537. Min Act: -0.0000

Data Index: 1339206 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.2993. Min Act: -0.0000

Data Index: 900861 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1545. Min Act: -0.0000

Data Index: 1102136 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 4.6552. Min Range: -4.6552

Max Act: 3.9832. Min Act: -0.0000

Data Index: 1066109 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1607. Min Act: -0.0000

Data Index: 587182 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 4.6552. Min Range: -4.6552

Max Act: 4.1205. Min Act: -0.0000

Data Index: 1341871 (C4 (Web Text))

Max Activating Token Index: 607