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

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

Neuron 6093 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.8613. Min Act: -0.0000

Data Index: 1378657 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6235. Min Act: -0.0000

Data Index: 1538063 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.5472. Min Act: -0.0000

Data Index: 1594164 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6733. Min Act: -0.0000

Data Index: 1616211 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6444. Min Act: -0.0000

Data Index: 1386665 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6082. Min Act: -0.0000

Data Index: 1609542 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.7347. Min Act: -0.0000

Data Index: 1532918 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1487534 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.5810. Min Act: -0.0000

Data Index: 1553147 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.5508. Min Act: -0.0000

Data Index: 1565653 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.5378. Min Act: -0.0000

Data Index: 1534131 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.4008. Min Act: -0.0000

Data Index: 1621660 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.5137. Min Act: -0.0000

Data Index: 1394591 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1490643 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6168. Min Act: -0.0000

Data Index: 1576311 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.4657. Min Act: -0.0000

Data Index: 1512944 (Python Code)

Max Activating Token Index: 1021

Text #16

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.6035. Min Act: -0.0000

Data Index: 1543089 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.3489. Min Act: -0.0000

Data Index: 1503386 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.4812. Min Act: -0.0000

Data Index: 1547657 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 2.8613. Min Range: -2.8613

Max Act: 2.4810. Min Act: -0.0000

Data Index: 1453015 (Python Code)

Max Activating Token Index: 471