Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 523 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.8067. Min Act: -0.1700

Data Index: 794105 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7900. Min Act: -0.1700

Data Index: 1030966 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7629. Min Act: -0.1700

Data Index: 493520 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7696. Min Act: -0.1700

Data Index: 523815 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7081. Min Act: -0.1700

Data Index: 1093933 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6620. Min Act: -0.1700

Data Index: 737082 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.7020. Min Act: -0.1700

Data Index: 1243580 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6920. Min Act: -0.1700

Data Index: 905049 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6710. Min Act: -0.1700

Data Index: 170578 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6684. Min Act: -0.1700

Data Index: 950006 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6050. Min Act: -0.1700

Data Index: 504370 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6613. Min Act: -0.1700

Data Index: 535422 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6513. Min Act: -0.1700

Data Index: 57200 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1096166 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6079. Min Act: -0.1700

Data Index: 845158 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6085. Min Act: -0.1700

Data Index: 694875 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.5991. Min Act: -0.1700

Data Index: 965035 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6181. Min Act: -0.1700

Data Index: 1036469 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1089038 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 3.8067. Min Range: -3.8067

Max Act: 3.6000. Min Act: -0.1700

Data Index: 792957 (C4 (Web Text))

Max Activating Token Index: 373