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

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

Neuron 2042 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: 0.5019. Min Range: -0.5019

Max Act: 0.5019. Min Act: -0.0000

Data Index: 892171 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.4250. Min Act: -0.0000

Data Index: 973993 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3881. Min Act: -0.0000

Data Index: 585773 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3707. Min Act: -0.0000

Data Index: 339225 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3640. Min Act: -0.0000

Data Index: 906871 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3416. Min Act: -0.0000

Data Index: 978270 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1026644 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3402. Min Act: -0.0000

Data Index: 691932 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3348. Min Act: -0.0000

Data Index: 398052 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1005309 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3664. Min Act: -0.0000

Data Index: 124524 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1109705 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1289000 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1017609 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3128. Min Act: -0.0000

Data Index: 457433 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.2865. Min Act: -0.0000

Data Index: 639479 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1160714 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3001. Min Act: -0.0000

Data Index: 301541 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3184. Min Act: -0.0000

Data Index: 809781 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.5019. Min Range: -0.5019

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1446492 (Python Code)

Max Activating Token Index: 817