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

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

Neuron 713 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: 0.2277. Min Range: -0.2277

Max Act: 0.2277. Min Act: -0.0001

Data Index: 433527 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2245. Min Act: -0.0001

Data Index: 517285 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2227. Min Act: -0.0001

Data Index: 205167 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1274781 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1117064 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2043. Min Act: -0.0001

Data Index: 423593 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1963. Min Act: -0.0001

Data Index: 614582 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2100. Min Act: -0.0001

Data Index: 20540 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1093129 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1854. Min Act: -0.0001

Data Index: 956507 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1837. Min Act: -0.0001

Data Index: 264229 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1897. Min Act: -0.0001

Data Index: 339533 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2029. Min Act: -0.0001

Data Index: 187479 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1869. Min Act: -0.0001

Data Index: 89307 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1157655 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1847. Min Act: -0.0001

Data Index: 326884 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1923. Min Act: -0.0001

Data Index: 51861 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1771. Min Act: -0.0001

Data Index: 416467 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1846. Min Act: -0.0001

Data Index: 172118 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1244384 (C4 (Web Text))

Max Activating Token Index: 728