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

Dataset: Open Web Text

Neuron 2796 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: 4.1221. Min Range: -4.1221

Max Act: 4.1221. Min Act: -0.1700

Data Index: 6438611 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9710. Min Act: -0.1700

Data Index: 1581180 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9763. Min Act: -0.1700

Data Index: 2924302 (Open Web Text)

Max Activating Token Index: 256

Text #3

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9799. Min Act: -0.1700

Data Index: 419014 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9422. Min Act: -0.1700

Data Index: 3315373 (Open Web Text)

Max Activating Token Index: 97

Text #5

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9392. Min Act: -0.1700

Data Index: 4285868 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8885. Min Act: -0.1700

Data Index: 2489254 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9181. Min Act: -0.1700

Data Index: 4591967 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9096. Min Act: -0.1700

Data Index: 892174 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9211. Min Act: -0.1700

Data Index: 2793601 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9087. Min Act: -0.1700

Data Index: 5873605 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8967. Min Act: -0.1700

Data Index: 78574 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9368. Min Act: -0.1700

Data Index: 404233 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.9171. Min Act: -0.1700

Data Index: 2438225 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8902. Min Act: -0.1700

Data Index: 4438088 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8799. Min Act: -0.1700

Data Index: 8757039 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8966. Min Act: -0.1700

Data Index: 7560007 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8808. Min Act: -0.1700

Data Index: 7296417 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8438. Min Act: -0.1700

Data Index: 5305945 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 4.1221. Min Range: -4.1221

Max Act: 3.8620. Min Act: -0.1700

Data Index: 1025894 (Open Web Text)

Max Activating Token Index: 39