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

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

Neuron 393 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8809. Min Act: -0.0000

Data Index: 28905 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7857. Min Act: -0.0000

Data Index: 31573 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5668. Min Act: -0.0000

Data Index: 1182304 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5428. Min Act: -0.0000

Data Index: 74240 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.6848. Min Act: -0.0000

Data Index: 154882 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5894. Min Act: -0.0000

Data Index: 508610 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7470. Min Act: -0.0000

Data Index: 161098 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5706. Min Act: -0.0000

Data Index: 1231247 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5198. Min Act: -0.0000

Data Index: 847511 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.4595. Min Act: -0.0000

Data Index: 960092 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5088. Min Act: -0.0000

Data Index: 360640 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.3324. Min Act: -0.0000

Data Index: 1022498 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.3180. Min Act: -0.0000

Data Index: 274711 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.3981. Min Act: -0.0000

Data Index: 512978 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.0722. Min Act: -0.0000

Data Index: 693441 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.5584. Min Act: -0.0000

Data Index: 423475 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.2069. Min Act: -0.0000

Data Index: 986004 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.2899. Min Act: -0.0000

Data Index: 387466 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.1254. Min Act: -0.0000

Data Index: 426023 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.1168. Min Act: -0.0000

Data Index: 522178 (C4 (Web Text))

Max Activating Token Index: 795