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

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

Neuron 378 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: 8.0614. Min Range: -8.0614

Max Act: 8.0614. Min Act: -0.1700

Data Index: 306243 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.8114. Min Act: -0.1700

Data Index: 969206 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.9364. Min Act: -0.1700

Data Index: 511448 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.4989. Min Act: -0.1700

Data Index: 1122666 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.3739. Min Act: -0.1700

Data Index: 341684 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.4989. Min Act: -0.1700

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.3114. Min Act: -0.1700

Data Index: 778684 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.3739. Min Act: -0.1700

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.2489. Min Act: -0.1700

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.2489. Min Act: -0.1700

Data Index: 139175 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.0614. Min Act: -0.1700

Data Index: 863871 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.0614. Min Act: -0.1700

Data Index: 580780 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.0614. Min Act: -0.1700

Data Index: 1332270 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.0614. Min Act: -0.1700

Data Index: 1188971 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.0614. Min Act: -0.1700

Data Index: 636152 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.1239. Min Act: -0.1700

Data Index: 137182 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 8.0614. Min Range: -8.0614

Max Act: 7.1864. Min Act: -0.1700

Data Index: 313721 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 8.0614. Min Range: -8.0614

Max Act: 6.9989. Min Act: -0.1700

Data Index: 678328 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 8.0614. Min Range: -8.0614

Max Act: 6.9989. Min Act: -0.1700

Data Index: 781460 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 8.0614. Min Range: -8.0614

Max Act: 6.9989. Min Act: -0.1700

Data Index: 1138670 (C4 (Web Text))

Max Activating Token Index: 891