Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 41 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.3123. Min Range: -3.3123

Max Act: 3.3123. Min Act: -0.1700

Data Index: 2443566 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.3123. Min Range: -3.3123

Max Act: 3.2387. Min Act: -0.1699

Data Index: 1734322 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3123. Min Range: -3.3123

Max Act: 3.0461. Min Act: -0.1700

Data Index: 1898755 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.3123. Min Range: -3.3123

Max Act: 3.0089. Min Act: -0.1698

Data Index: 4162368 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.9373. Min Act: -0.1700

Data Index: 709611 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.8461. Min Act: -0.1700

Data Index: 6050872 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.8112. Min Act: -0.1700

Data Index: 7267414 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.8297. Min Act: -0.1699

Data Index: 1081146 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.8268. Min Act: -0.1700

Data Index: 1971903 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.8049. Min Act: -0.1700

Data Index: 7975834 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7885. Min Act: -0.1700

Data Index: 3161047 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7730. Min Act: -0.1700

Data Index: 3550157 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7792. Min Act: -0.1700

Data Index: 2766065 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7816. Min Act: -0.1700

Data Index: 3235212 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7726. Min Act: -0.1700

Data Index: 6686220 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7610. Min Act: -0.1700

Data Index: 5013161 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7442. Min Act: -0.1700

Data Index: 386784 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7193. Min Act: -0.1700

Data Index: 5229149 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7391. Min Act: -0.1700

Data Index: 813735 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.3123. Min Range: -3.3123

Max Act: 2.7398. Min Act: -0.1700

Data Index: 4628026 (Open Web Text)

Max Activating Token Index: 1023