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

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

Neuron 1232 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.2073. Min Act: -0.1700

Data Index: 1156213 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.1915. Min Act: -0.1700

Data Index: 706306 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.1128. Min Act: -0.1700

Data Index: 1292969 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0970. Min Act: -0.1700

Data Index: 1306635 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0497. Min Act: -0.1700

Data Index: 1071931 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0497. Min Act: -0.1700

Data Index: 1277859 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0497. Min Act: -0.1700

Data Index: 424461 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0497. Min Act: -0.1700

Data Index: 1339667 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0655. Min Act: -0.1700

Data Index: 225036 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0181. Min Act: -0.1700

Data Index: 884755 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0339. Min Act: -0.1700

Data Index: 1355441 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0181. Min Act: -0.1700

Data Index: 1354784 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0181. Min Act: -0.1700

Data Index: 544714 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1338550 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1111684 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0023. Min Act: -0.1700

Data Index: 227744 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0023. Min Act: -0.1700

Data Index: 568570 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 3.2073. Min Range: -3.2073

Max Act: 2.9865. Min Act: -0.1700

Data Index: 898048 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.2073. Min Range: -3.2073

Max Act: 2.9865. Min Act: -0.1700

Data Index: 112873 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.2073. Min Range: -3.2073

Max Act: 3.0023. Min Act: -0.1700

Data Index: 885615 (C4 (Web Text))

Max Activating Token Index: 397