Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.7956. Min Act: -0.0001

Data Index: 387901 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.7077. Min Act: -0.0001

Data Index: 644530 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.2218. Min Act: -0.0001

Data Index: 131046 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.2552. Min Act: -0.0001

Data Index: 115668 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.3804. Min Act: -0.0001

Data Index: 567783 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.2219. Min Act: -0.0001

Data Index: 239495 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.0694. Min Act: -0.0001

Data Index: 565029 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.9877. Min Act: -0.0001

Data Index: 220194 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8548. Min Act: -0.0001

Data Index: 460735 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.1182. Min Act: -0.0001

Data Index: 758810 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8646. Min Act: -0.0001

Data Index: 880039 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 3.7956. Min Range: -3.7956

Max Act: 3.0403. Min Act: -0.0001

Data Index: 505467 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8767. Min Act: -0.0001

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.6004. Min Act: -0.0001

Data Index: 878938 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.9929. Min Act: -0.0001

Data Index: 502448 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8430. Min Act: -0.0001

Data Index: 940375 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8338. Min Act: -0.0001

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.8020. Min Act: -0.0001

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.9501. Min Act: -0.0001

Data Index: 1023708 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.7956. Min Range: -3.7956

Max Act: 2.5061. Min Act: -0.0001

Data Index: 258983 (C4 (Web Text))

Max Activating Token Index: 845