Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.9426. Min Act: -0.0001

Data Index: 766606 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.9007. Min Act: -0.0001

Data Index: 546085 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8713. Min Act: -0.0001

Data Index: 338998 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8323. Min Act: -0.0001

Data Index: 419220 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8889. Min Act: -0.0001

Data Index: 149108 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8081. Min Act: -0.0001

Data Index: 260532 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7982. Min Act: -0.0001

Data Index: 982716 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8145. Min Act: -0.0001

Data Index: 338047 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8321. Min Act: -0.0001

Data Index: 599266 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1093466 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7745. Min Act: -0.0001

Data Index: 108227 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7870. Min Act: -0.0001

Data Index: 188608 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7639. Min Act: -0.0001

Data Index: 946058 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7266. Min Act: -0.0001

Data Index: 620447 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8014. Min Act: -0.0001

Data Index: 189850 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7939. Min Act: -0.0001

Data Index: 204973 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6998. Min Act: -0.0001

Data Index: 495833 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7356. Min Act: -0.0001

Data Index: 64982 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7941. Min Act: -0.0001

Data Index: 116561 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7567. Min Act: -0.0001

Data Index: 611416 (C4 (Web Text))

Max Activating Token Index: 849