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

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

Neuron 1501 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: 7.8710. Min Range: -7.8710

Max Act: 7.6835. Min Act: -0.1700

Data Index: 619280 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.3085. Min Act: -0.1700

Data Index: 713981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.8710. Min Act: -0.1700

Data Index: 615326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.5585. Min Act: -0.1700

Data Index: 949189 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.4960. Min Act: -0.1700

Data Index: 364679 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.4335. Min Act: -0.1700

Data Index: 34913 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.2460. Min Act: -0.1700

Data Index: 318652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.3085. Min Act: -0.1700

Data Index: 369818 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1522. Min Act: -0.1700

Data Index: 1346726 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1522. Min Act: -0.1700

Data Index: 72334 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.2772. Min Act: -0.1700

Data Index: 727253 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1835. Min Act: -0.1700

Data Index: 105153 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.0585. Min Act: -0.1700

Data Index: 473356 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1522. Min Act: -0.1700

Data Index: 894394 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.0897. Min Act: -0.1700

Data Index: 796786 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.0897. Min Act: -0.1700

Data Index: 287237 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1522. Min Act: -0.1700

Data Index: 170069 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.2460. Min Act: -0.1700

Data Index: 101080 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 7.8710. Min Range: -7.8710

Max Act: 7.1522. Min Act: -0.1700

Data Index: 127704 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 7.8710. Min Range: -7.8710

Max Act: 6.8397. Min Act: -0.1700

Data Index: 695805 (C4 (Web Text))

Max Activating Token Index: 222