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

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

Neuron 1504 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: 1.4252. Min Range: -1.4252

Max Act: 1.4252. Min Act: -0.1700

Data Index: 449457 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3547. Min Act: -0.1700

Data Index: 667818 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3547. Min Act: -0.1700

Data Index: 446483 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3371. Min Act: -0.1700

Data Index: 1287444 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3194. Min Act: -0.1700

Data Index: 1640972 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3106. Min Act: -0.1700

Data Index: 1100765 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.3018. Min Act: -0.1700

Data Index: 70233 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2930. Min Act: -0.1700

Data Index: 1342788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2753. Min Act: -0.1700

Data Index: 895293 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2753. Min Act: -0.1700

Data Index: 369408 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2665. Min Act: -0.1700

Data Index: 1357091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2665. Min Act: -0.1700

Data Index: 220200 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2753. Min Act: -0.1700

Data Index: 646601 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2665. Min Act: -0.1700

Data Index: 430519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2665. Min Act: -0.1700

Data Index: 503473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2753. Min Act: -0.1700

Data Index: 562367 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2665. Min Act: -0.1700

Data Index: 1290212 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2577. Min Act: -0.1700

Data Index: 1142606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2577. Min Act: -0.1700

Data Index: 343160 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.4252. Min Range: -1.4252

Max Act: 1.2489. Min Act: -0.1700

Data Index: 1239137 (C4 (Web Text))

Max Activating Token Index: 794