Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1039 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1301950 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.2179. Min Act: -0.1700

Data Index: 343177 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1867. Min Act: -0.1700

Data Index: 565633 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1312823 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1554. Min Act: -0.1700

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1867. Min Act: -0.1700

Data Index: 748318 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1554. Min Act: -0.1700

Data Index: 337494 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0617. Min Act: -0.1700

Data Index: 60392 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0617. Min Act: -0.1700

Data Index: 174672 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0929. Min Act: -0.1700

Data Index: 891532 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0617. Min Act: -0.1700

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0304. Min Act: -0.1700

Data Index: 1288410 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 5.2179. Min Range: -5.2179

Max Act: 4.9992. Min Act: -0.1700

Data Index: 869162 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0304. Min Act: -0.1700

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0304. Min Act: -0.1700

Data Index: 1318718 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0304. Min Act: -0.1700

Data Index: 1191403 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.1242. Min Act: -0.1700

Data Index: 539646 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 5.2179. Min Range: -5.2179

Max Act: 4.9992. Min Act: -0.1700

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 5.2179. Min Range: -5.2179

Max Act: 4.9992. Min Act: -0.1700

Data Index: 1212958 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 5.2179. Min Range: -5.2179

Max Act: 5.0617. Min Act: -0.1700

Data Index: 438369 (C4 (Web Text))

Max Activating Token Index: 278