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

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

Neuron 4582 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: 4.8533. Min Range: -4.8533

Max Act: 4.8533. Min Act: -0.0000

Data Index: 489009 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 4.8533. Min Range: -4.8533

Max Act: 4.5600. Min Act: -0.0000

Data Index: 920985 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 4.8533. Min Range: -4.8533

Max Act: 4.1374. Min Act: -0.0000

Data Index: 655649 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.9885. Min Act: -0.0000

Data Index: 563776 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.8529. Min Act: -0.0000

Data Index: 938962 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.7025. Min Act: -0.0000

Data Index: 1027214 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.8939. Min Act: -0.0000

Data Index: 877991 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.5564. Min Act: -0.0000

Data Index: 853284 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.5270. Min Act: -0.0000

Data Index: 699009 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.5152. Min Act: -0.0000

Data Index: 1006540 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.5040. Min Act: -0.0000

Data Index: 40010 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.2094. Min Act: -0.0000

Data Index: 371363 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.6038. Min Act: -0.0000

Data Index: 295466 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.4057. Min Act: -0.0000

Data Index: 116960 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.2517. Min Act: -0.0000

Data Index: 1055539 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.3726. Min Act: -0.0000

Data Index: 439370 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.7010. Min Act: -0.0000

Data Index: 401199 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.5068. Min Act: -0.0000

Data Index: 450099 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.6620. Min Act: -0.0000

Data Index: 1094720 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 4.8533. Min Range: -4.8533

Max Act: 3.3162. Min Act: -0.0000

Data Index: 1174664 (C4 (Web Text))

Max Activating Token Index: 172