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

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

Neuron 3215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0522. Min Range: -6.0522

Max Act: 6.0522. Min Act: -0.0001

Data Index: 1354465 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 6.0522. Min Range: -6.0522

Max Act: 5.0621. Min Act: -0.0000

Data Index: 51033 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.8414. Min Act: -0.0000

Data Index: 1309509 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.8648. Min Act: -0.0001

Data Index: 598302 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.7890. Min Act: -0.0000

Data Index: 1109171 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.9484. Min Act: -0.0000

Data Index: 559989 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.3747. Min Act: -0.0001

Data Index: 582876 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.6878. Min Act: -0.0000

Data Index: 46180 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.5040. Min Act: -0.0000

Data Index: 828385 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.6807. Min Act: -0.0000

Data Index: 215603 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.5672. Min Act: -0.0001

Data Index: 904634 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.3921. Min Act: -0.0000

Data Index: 67758 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.5287. Min Act: -0.0000

Data Index: 1073892 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.4834. Min Act: -0.0000

Data Index: 1339245 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.7700. Min Act: -0.0000

Data Index: 1295658 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.4274. Min Act: -0.0001

Data Index: 833957 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.3944. Min Act: -0.0000

Data Index: 588506 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.3777. Min Act: -0.0001

Data Index: 264123 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.1903. Min Act: -0.0000

Data Index: 734442 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 6.0522. Min Range: -6.0522

Max Act: 4.1756. Min Act: -0.0000

Data Index: 311931 (C4 (Web Text))

Max Activating Token Index: 371