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

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

Neuron 847 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: 12.0374. Min Range: -12.0374

Max Act: 12.0374. Min Act: -0.1700

Data Index: 1537157 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.9749. Min Act: -0.1700

Data Index: 1494834 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.9124. Min Act: -0.1700

Data Index: 796182 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.7874. Min Act: -0.1700

Data Index: 1454602 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.5374. Min Act: -0.1700

Data Index: 154158 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4124. Min Act: -0.1700

Data Index: 180771 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4749. Min Act: -0.1700

Data Index: 379700 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.7249. Min Act: -0.1700

Data Index: 1306483 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.3499. Min Act: -0.1700

Data Index: 678533 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.3499. Min Act: -0.1700

Data Index: 239583 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4124. Min Act: -0.1700

Data Index: 44885 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4749. Min Act: -0.1700

Data Index: 291437 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4749. Min Act: -0.1700

Data Index: 1126956 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.2874. Min Act: -0.1700

Data Index: 1320296 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4749. Min Act: -0.1700

Data Index: 9328 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.2249. Min Act: -0.1700

Data Index: 227904 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4124. Min Act: -0.1700

Data Index: 108561 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.2249. Min Act: -0.1700

Data Index: 26038 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.2874. Min Act: -0.1700

Data Index: 763787 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 12.0374. Min Range: -12.0374

Max Act: 11.4749. Min Act: -0.1700

Data Index: 587222 (C4 (Web Text))

Max Activating Token Index: 994