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

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

Neuron 4129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5608. Min Range: -4.5608

Max Act: 4.5608. Min Act: -0.0000

Data Index: 1351101 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 4.5608. Min Range: -4.5608

Max Act: 4.4321. Min Act: -0.0000

Data Index: 1335807 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 4.5608. Min Range: -4.5608

Max Act: 4.1159. Min Act: -0.0000

Data Index: 85286 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 4.5608. Min Range: -4.5608

Max Act: 4.0486. Min Act: -0.0000

Data Index: 371775 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.7861. Min Act: -0.0000

Data Index: 83638 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.8973. Min Act: -0.0000

Data Index: 246228 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.9019. Min Act: -0.0000

Data Index: 1023480 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.8327. Min Act: -0.0000

Data Index: 694261 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.7109. Min Act: -0.0000

Data Index: 1117475 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.5327. Min Act: -0.0000

Data Index: 70127 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.2402. Min Act: -0.0000

Data Index: 217964 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.4091. Min Act: -0.0000

Data Index: 1083123 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.1959. Min Act: -0.0000

Data Index: 97350 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 4.5608. Min Range: -4.5608

Max Act: 2.8824. Min Act: -0.0000

Data Index: 1327172 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.3205. Min Act: -0.0000

Data Index: 1252214 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.2918. Min Act: -0.0000

Data Index: 537706 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.4457. Min Act: -0.0000

Data Index: 1034673 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.2591. Min Act: -0.0000

Data Index: 292828 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.2825. Min Act: -0.0000

Data Index: 305176 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 4.5608. Min Range: -4.5608

Max Act: 3.2155. Min Act: -0.0000

Data Index: 437404 (C4 (Web Text))

Max Activating Token Index: 972