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

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

Neuron 308 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.4691. Min Act: -0.1700

Data Index: 1512977 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.4377. Min Act: -0.1700

Data Index: 1394223 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1368693 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1410437 (Python Code)

Max Activating Token Index: 505

Text #4

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1417937 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1417674 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3279. Min Act: -0.1700

Data Index: 1638472 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3122. Min Act: -0.1700

Data Index: 1432966 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3279. Min Act: -0.1700

Data Index: 1476224 (Python Code)

Max Activating Token Index: 529

Text #9

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.3122. Min Act: -0.1700

Data Index: 1413019 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2965. Min Act: -0.1700

Data Index: 1597463 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2965. Min Act: -0.1700

Data Index: 1602825 (Python Code)

Max Activating Token Index: 994

Text #12

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1629227 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1602367 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2651. Min Act: -0.1700

Data Index: 1399512 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2651. Min Act: -0.1700

Data Index: 1582385 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2493. Min Act: -0.1700

Data Index: 1538138 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2179. Min Act: -0.1700

Data Index: 1579433 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2651. Min Act: -0.1700

Data Index: 1614964 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 3.4691. Min Range: -3.4691

Max Act: 3.2179. Min Act: -0.1700

Data Index: 1451014 (Python Code)

Max Activating Token Index: 249