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

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

Neuron 310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1522. Min Range: -5.1522

Max Act: 5.1522. Min Act: -0.1700

Data Index: 735073 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 5.1522. Min Range: -5.1522

Max Act: 5.0585. Min Act: -0.1700

Data Index: 190941 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 5.1522. Min Range: -5.1522

Max Act: 5.0585. Min Act: -0.1700

Data Index: 469573 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9960. Min Act: -0.1700

Data Index: 191709 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9960. Min Act: -0.1700

Data Index: 577237 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9960. Min Act: -0.1700

Data Index: 1219724 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9022. Min Act: -0.1700

Data Index: 421577 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9335. Min Act: -0.1700

Data Index: 1260355 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9022. Min Act: -0.1700

Data Index: 1049664 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8710. Min Act: -0.1700

Data Index: 1263875 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9022. Min Act: -0.1700

Data Index: 93061 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9335. Min Act: -0.1700

Data Index: 1333440 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9022. Min Act: -0.1700

Data Index: 683132 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9335. Min Act: -0.1700

Data Index: 193508 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8710. Min Act: -0.1700

Data Index: 413025 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8085. Min Act: -0.1700

Data Index: 812106 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.9022. Min Act: -0.1700

Data Index: 188982 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8710. Min Act: -0.1700

Data Index: 410165 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8710. Min Act: -0.1700

Data Index: 279475 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 5.1522. Min Range: -5.1522

Max Act: 4.8710. Min Act: -0.1700

Data Index: 428908 (C4 (Web Text))

Max Activating Token Index: 800