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

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

Neuron 874 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: 5.2802. Min Range: -5.2802

Max Act: 5.2802. Min Act: -0.1700

Data Index: 700576 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.2802. Min Range: -5.2802

Max Act: 5.0927. Min Act: -0.1700

Data Index: 134956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.2802. Min Range: -5.2802

Max Act: 5.1240. Min Act: -0.1700

Data Index: 1555165 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 5.2802. Min Range: -5.2802

Max Act: 5.0615. Min Act: -0.1700

Data Index: 526026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.9365. Min Act: -0.1700

Data Index: 521497 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.8740. Min Act: -0.1700

Data Index: 1574809 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.8740. Min Act: -0.1700

Data Index: 1244892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.8740. Min Act: -0.1700

Data Index: 1503668 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.8740. Min Act: -0.1700

Data Index: 967603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.7177. Min Act: -0.1700

Data Index: 1655901 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.7802. Min Act: -0.1700

Data Index: 453153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6865. Min Act: -0.1700

Data Index: 1563187 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6552. Min Act: -0.1700

Data Index: 1619327 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6865. Min Act: -0.1700

Data Index: 901052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6552. Min Act: -0.1700

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6865. Min Act: -0.1700

Data Index: 1218161 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.6240. Min Act: -0.1700

Data Index: 1476478 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.5927. Min Act: -0.1700

Data Index: 97406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.5927. Min Act: -0.1700

Data Index: 431085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.2802. Min Range: -5.2802

Max Act: 4.5615. Min Act: -0.1700

Data Index: 147634 (C4 (Web Text))

Max Activating Token Index: 1023