Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.4939. Min Act: -0.1700

Data Index: 1451077 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.4469. Min Act: -0.1700

Data Index: 1484336 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.4626. Min Act: -0.1700

Data Index: 1618246 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.4155. Min Act: -0.1700

Data Index: 1529277 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3998. Min Act: -0.1700

Data Index: 1587820 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1515850 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1527096 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1489296 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1495687 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1486132 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1372682 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3528. Min Act: -0.1700

Data Index: 1410445 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1537483 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3214. Min Act: -0.1700

Data Index: 1582695 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1624243 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1409331 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1487523 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.2900. Min Act: -0.1700

Data Index: 1573197 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1505529 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 3.4939. Min Range: -3.4939

Max Act: 3.2428. Min Act: -0.1700

Data Index: 1523564 (Python Code)

Max Activating Token Index: 319