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

Dataset: Open Web Text

Neuron 1845 in Layer 0

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: 2.8368. Min Range: -2.8368

Max Act: 2.8368. Min Act: -0.1700

Data Index: 3687461 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.8171. Min Act: -0.1700

Data Index: 1450310 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.8158. Min Act: -0.1700

Data Index: 855008 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.8139. Min Act: -0.1700

Data Index: 6790768 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.8003. Min Act: -0.1700

Data Index: 2825956 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7739. Min Act: -0.1700

Data Index: 1668235 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7741. Min Act: -0.1700

Data Index: 79904 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7767. Min Act: -0.1700

Data Index: 5779886 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7807. Min Act: -0.1700

Data Index: 7908547 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7829. Min Act: -0.1700

Data Index: 7606383 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7711. Min Act: -0.1700

Data Index: 3355880 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7763. Min Act: -0.1700

Data Index: 4416389 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7755. Min Act: -0.1700

Data Index: 6749646 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7649. Min Act: -0.1700

Data Index: 5575789 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7628. Min Act: -0.1700

Data Index: 76289 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7708. Min Act: -0.1700

Data Index: 6441992 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7612. Min Act: -0.1700

Data Index: 3031770 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7681. Min Act: -0.1700

Data Index: 4026899 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7675. Min Act: -0.1700

Data Index: 489406 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8368. Min Range: -2.8368

Max Act: 2.7545. Min Act: -0.1700

Data Index: 183672 (Open Web Text)

Max Activating Token Index: 41