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

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

Neuron 2872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5934. Min Act: -0.0002

Data Index: 762107 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4254. Min Act: -0.0002

Data Index: 820752 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4145. Min Act: -0.0002

Data Index: 1125076 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3511. Min Act: -0.0002

Data Index: 823277 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3238. Min Act: -0.0002

Data Index: 1305525 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3020. Min Act: -0.0002

Data Index: 60680 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2939. Min Act: -0.0002

Data Index: 37994 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2903. Min Act: -0.0002

Data Index: 106270 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2888. Min Act: -0.0002

Data Index: 457698 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2842. Min Act: -0.0002

Data Index: 898673 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2818. Min Act: -0.0002

Data Index: 585840 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2839. Min Act: -0.0002

Data Index: 1071721 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2703. Min Act: -0.0002

Data Index: 599859 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2548. Min Act: -0.0002

Data Index: 793218 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2583. Min Act: -0.0002

Data Index: 693753 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2668. Min Act: -0.0002

Data Index: 832144 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2491. Min Act: -0.0002

Data Index: 131299 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2454. Min Act: -0.0002

Data Index: 871158 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2362. Min Act: -0.0002

Data Index: 332448 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.2498. Min Act: -0.0002

Data Index: 967064 (C4 (Web Text))

Max Activating Token Index: 493