Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.5922. Min Act: -0.1700

Data Index: 342851 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.3735. Min Act: -0.1700

Data Index: 80402 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.3110. Min Act: -0.1700

Data Index: 777128 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.3735. Min Act: -0.1700

Data Index: 447541 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.2172. Min Act: -0.1700

Data Index: 483773 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.3422. Min Act: -0.1700

Data Index: 559473 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.3422. Min Act: -0.1700

Data Index: 1311400 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.2485. Min Act: -0.1700

Data Index: 468950 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.2485. Min Act: -0.1700

Data Index: 816583 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1169522 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.2485. Min Act: -0.1700

Data Index: 620225 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1860. Min Act: -0.1700

Data Index: 277447 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1860. Min Act: -0.1700

Data Index: 66090 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1547. Min Act: -0.1700

Data Index: 1271591 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.2172. Min Act: -0.1700

Data Index: 1343470 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1860. Min Act: -0.1700

Data Index: 503774 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1088279 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1547. Min Act: -0.1700

Data Index: 1324359 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1192677 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 5.5922. Min Range: -5.5922

Max Act: 5.1235. Min Act: -0.1700

Data Index: 975002 (C4 (Web Text))

Max Activating Token Index: 724