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

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

Neuron 4439 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1630187 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8887. Min Act: 0.0000

Data Index: 1617844 (Python Code)

Max Activating Token Index: 309

Text #2

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7877. Min Act: -0.0000

Data Index: 318111 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1373406 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1415442 (Python Code)

Max Activating Token Index: 962

Text #5

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1543225 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1378743 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1362780 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7648. Min Act: 0.0000

Data Index: 1521860 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1558312 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1501836 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6657. Min Act: -0.0000

Data Index: 74016 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1034025 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1452148 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1129071 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6562. Min Act: -0.0000

Data Index: 525630 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1018970 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6395. Min Act: -0.0000

Data Index: 462293 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1444057 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.8887. Min Range: -0.8887

Max Act: 0.6559. Min Act: 0.0000

Data Index: 1626172 (Python Code)

Max Activating Token Index: 941