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

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

Neuron 392 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0001

Data Index: 937053 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2437. Min Act: -0.0000

Data Index: 38286 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2462. Min Act: -0.0000

Data Index: 223855 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2451. Min Act: -0.0000

Data Index: 775607 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2408. Min Act: -0.0000

Data Index: 100805 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2327. Min Act: -0.0000

Data Index: 767264 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2295. Min Act: -0.0000

Data Index: 620726 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2284. Min Act: -0.0000

Data Index: 625451 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2108. Min Act: -0.0000

Data Index: 676966 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2166. Min Act: -0.0000

Data Index: 314894 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1016855 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1156763 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2050. Min Act: 0.0001

Data Index: 1310240 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1197507 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2038. Min Act: -0.0001

Data Index: 334705 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1968. Min Act: -0.0000

Data Index: 242800 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1974. Min Act: -0.0000

Data Index: 273983 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2033. Min Act: -0.0000

Data Index: 205005 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1996. Min Act: -0.0000

Data Index: 886813 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1033754 (C4 (Web Text))

Max Activating Token Index: 63