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

Dataset: Open Web Text

Neuron 1073 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: 2.8445. Min Range: -2.8445

Max Act: 2.8445. Min Act: -0.1700

Data Index: 8051649 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.8196. Min Act: -0.1700

Data Index: 2442109 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7950. Min Act: -0.1700

Data Index: 4905479 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7814. Min Act: -0.1700

Data Index: 3827316 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7814. Min Act: -0.1700

Data Index: 2664790 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7587. Min Act: -0.1700

Data Index: 3033990 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7598. Min Act: -0.1700

Data Index: 2988218 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7615. Min Act: -0.1700

Data Index: 6212010 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7492. Min Act: -0.1700

Data Index: 5575538 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7538. Min Act: -0.1700

Data Index: 3901444 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7378. Min Act: -0.1700

Data Index: 659666 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7333. Min Act: -0.1700

Data Index: 3340416 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7319. Min Act: -0.1700

Data Index: 5214698 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7084. Min Act: -0.1700

Data Index: 779310 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7107. Min Act: -0.1700

Data Index: 5346168 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7084. Min Act: -0.1700

Data Index: 7222007 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7019. Min Act: -0.1700

Data Index: 6942289 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.6973. Min Act: -0.1700

Data Index: 153209 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.6888. Min Act: -0.1700

Data Index: 6582533 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.6963. Min Act: -0.1700

Data Index: 6590781 (Open Web Text)

Max Activating Token Index: 3