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

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

Neuron 936 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.1938. Min Act: -0.1700

Data Index: 30244 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.1151. Min Act: -0.1700

Data Index: 905952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0678. Min Act: -0.1700

Data Index: 172746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0520. Min Act: -0.1700

Data Index: 358856 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0362. Min Act: -0.1700

Data Index: 847120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0362. Min Act: -0.1700

Data Index: 312436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0520. Min Act: -0.1700

Data Index: 149676 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0362. Min Act: -0.1700

Data Index: 720471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0204. Min Act: -0.1700

Data Index: 514135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0046. Min Act: -0.1700

Data Index: 70990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9888. Min Act: -0.1700

Data Index: 1191828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0046. Min Act: -0.1700

Data Index: 386538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9888. Min Act: -0.1700

Data Index: 160701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9888. Min Act: -0.1700

Data Index: 1297780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9730. Min Act: -0.1700

Data Index: 673064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9571. Min Act: -0.1700

Data Index: 259989 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9413. Min Act: -0.1700

Data Index: 744667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9730. Min Act: -0.1700

Data Index: 859638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9413. Min Act: -0.1700

Data Index: 993377 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9730. Min Act: -0.1700

Data Index: 97566 (C4 (Web Text))

Max Activating Token Index: 1023