Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.4197. Min Act: -0.0000

Data Index: 740160 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.1253. Min Act: -0.0000

Data Index: 843609 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.5934. Min Act: -0.0000

Data Index: 1221042 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.2812. Min Act: -0.0001

Data Index: 911086 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.2885. Min Act: -0.0000

Data Index: 213200 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.5934. Min Range: -2.5934

Max Act: 2.3116. Min Act: -0.0000

Data Index: 32685 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.9065. Min Act: -0.0000

Data Index: 506295 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1263033 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.9653. Min Act: -0.0001

Data Index: 239569 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.8548. Min Act: -0.0000

Data Index: 206798 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.8596. Min Act: -0.0000

Data Index: 941609 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.6321. Min Act: -0.0001

Data Index: 13588 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.7986. Min Act: -0.0000

Data Index: 429411 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.9152. Min Act: -0.0000

Data Index: 856729 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.7766. Min Act: -0.0000

Data Index: 191629 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.6841. Min Act: -0.0000

Data Index: 677451 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.7679. Min Act: -0.0000

Data Index: 459853 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.6787. Min Act: -0.0000

Data Index: 250012 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.7470. Min Act: -0.0000

Data Index: 1272467 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 2.5934. Min Range: -2.5934

Max Act: 1.8782. Min Act: -0.0000

Data Index: 544522 (C4 (Web Text))

Max Activating Token Index: 737