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

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

Neuron 107 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: 3.6795. Min Range: -3.6795

Max Act: 3.6795. Min Act: -0.1700

Data Index: 673782 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.6042. Min Act: -0.1699

Data Index: 227069 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5972. Min Act: -0.1700

Data Index: 1007839 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5400. Min Act: -0.1700

Data Index: 975221 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5336. Min Act: -0.1699

Data Index: 320950 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5038. Min Act: -0.1700

Data Index: 862865 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1274583 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4935. Min Act: -0.1699

Data Index: 83652 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.5022. Min Act: -0.1699

Data Index: 1251349 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4876. Min Act: -0.1700

Data Index: 153768 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4639. Min Act: -0.1699

Data Index: 4291 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4809. Min Act: -0.1699

Data Index: 1136408 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4567. Min Act: -0.1700

Data Index: 974751 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4441. Min Act: -0.1700

Data Index: 869059 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4289. Min Act: -0.1694

Data Index: 827460 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4155. Min Act: -0.1700

Data Index: 683867 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4129. Min Act: -0.1699

Data Index: 941876 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.3990. Min Act: -0.1700

Data Index: 52517 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.3970. Min Act: -0.1699

Data Index: 752820 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 3.6795. Min Range: -3.6795

Max Act: 3.4044. Min Act: -0.1700

Data Index: 754870 (C4 (Web Text))

Max Activating Token Index: 66