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

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

Neuron 1988 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7915. Min Act: -0.0000

Data Index: 852935 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1133394 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5606. Min Act: -0.0001

Data Index: 1112911 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5224. Min Act: -0.0001

Data Index: 100142 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1215246 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1030148 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4480. Min Act: -0.0001

Data Index: 152534 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4479. Min Act: -0.0000

Data Index: 488257 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4361. Min Act: -0.0000

Data Index: 117199 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4356. Min Act: -0.0001

Data Index: 827858 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4342. Min Act: 0.0000

Data Index: 962611 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1202133 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.3892. Min Act: -0.0000

Data Index: 873763 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4025. Min Act: -0.0000

Data Index: 734957 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4008. Min Act: -0.0001

Data Index: 942178 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4114. Min Act: -0.0000

Data Index: 195757 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.3947. Min Act: -0.0001

Data Index: 1256313 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4045. Min Act: -0.0000

Data Index: 740168 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4048. Min Act: -0.0000

Data Index: 199236 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.3747. Min Act: -0.0001

Data Index: 897797 (C4 (Web Text))

Max Activating Token Index: 695