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

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

Neuron 1494 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: 3.0531. Min Range: -3.0531

Max Act: 3.0531. Min Act: -0.0000

Data Index: 1508287 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.9827. Min Act: -0.0000

Data Index: 1581924 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8573. Min Act: -0.0000

Data Index: 1456089 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.9676. Min Act: -0.0000

Data Index: 1596835 (Python Code)

Max Activating Token Index: 719

Text #4

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.6583. Min Act: -0.0000

Data Index: 912324 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4688. Min Act: -0.0000

Data Index: 1585471 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.7183. Min Act: -0.0000

Data Index: 1466577 (Python Code)

Max Activating Token Index: 333

Text #7

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.5548. Min Act: -0.0000

Data Index: 690893 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.6169. Min Act: -0.0000

Data Index: 98662 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4485. Min Act: -0.0000

Data Index: 681051 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4261. Min Act: -0.0000

Data Index: 1565420 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4677. Min Act: -0.0000

Data Index: 1558483 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.3256. Min Act: -0.0000

Data Index: 1595819 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.3140. Min Act: -0.0000

Data Index: 1476252 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.3078. Min Act: -0.0000

Data Index: 1556676 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.3155. Min Act: -0.0000

Data Index: 59669 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1541533 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.2717. Min Act: -0.0000

Data Index: 1590366 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.2505. Min Act: -0.0000

Data Index: 1153050 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1413343 (Python Code)

Max Activating Token Index: 2