Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1260816 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1156761 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3637. Min Act: -0.0000

Data Index: 699745 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3454. Min Act: -0.0000

Data Index: 363640 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3436. Min Act: -0.0000

Data Index: 57639 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.3405. Min Act: -0.0000

Data Index: 479794 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2697. Min Act: -0.0000

Data Index: 938178 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2710. Min Act: -0.0000

Data Index: 385375 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2768. Min Act: -0.0000

Data Index: 362704 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2604. Min Act: -0.0000

Data Index: 34158 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2488. Min Act: -0.0000

Data Index: 638258 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2310. Min Act: -0.0000

Data Index: 680338 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1240407 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1309649 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1083273 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2099. Min Act: -0.0000

Data Index: 625974 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.1991. Min Act: -0.0000

Data Index: 777959 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.1884. Min Act: -0.0000

Data Index: 398052 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1023565 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3964. Min Range: -0.3964

Max Act: 0.2052. Min Act: -0.0000

Data Index: 440078 (C4 (Web Text))

Max Activating Token Index: 232