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

Dataset: Open Web Text

Neuron 348 in Layer 1

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: 1.8442. Min Range: -1.8442

Max Act: 1.8442. Min Act: -0.1700

Data Index: 1231363 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.8102. Min Act: -0.1700

Data Index: 5468615 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7963. Min Act: -0.1700

Data Index: 1353697 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7928. Min Act: -0.1700

Data Index: 7565825 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7841. Min Act: -0.1699

Data Index: 7291829 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7930. Min Act: -0.1700

Data Index: 7558993 (Open Web Text)

Max Activating Token Index: 66

Text #6

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7807. Min Act: -0.1700

Data Index: 3949270 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7751. Min Act: -0.1700

Data Index: 2235206 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7723. Min Act: -0.1699

Data Index: 7558992 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7825. Min Act: -0.1700

Data Index: 686492 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7899. Min Act: -0.1700

Data Index: 2271139 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7885. Min Act: -0.1700

Data Index: 949342 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7770. Min Act: -0.1700

Data Index: 5031854 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7683. Min Act: -0.1700

Data Index: 8391971 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7735. Min Act: -0.1700

Data Index: 929129 (Open Web Text)

Max Activating Token Index: 37

Text #15

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7726. Min Act: -0.1700

Data Index: 903674 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7687. Min Act: -0.1700

Data Index: 7059241 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7584. Min Act: -0.1700

Data Index: 5466389 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7683. Min Act: -0.1700

Data Index: 1852637 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.8442. Min Range: -1.8442

Max Act: 1.7637. Min Act: -0.1700

Data Index: 1780156 (Open Web Text)

Max Activating Token Index: 4