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

Dataset: Open Web Text

Neuron 854 in Layer 5

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: 3.9953. Min Range: -3.9953

Max Act: 3.9953. Min Act: -0.1700

Data Index: 8692272 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.8196. Min Act: -0.1700

Data Index: 4523168 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7454. Min Act: -0.1700

Data Index: 7059090 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7545. Min Act: -0.1700

Data Index: 3808296 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7170. Min Act: -0.1700

Data Index: 4414650 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7409. Min Act: -0.1700

Data Index: 7132212 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7345. Min Act: -0.1700

Data Index: 6212322 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.7036. Min Act: -0.1700

Data Index: 959593 (Open Web Text)

Max Activating Token Index: 323

Text #8

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6857. Min Act: -0.1700

Data Index: 5365279 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6352. Min Act: -0.1700

Data Index: 7949602 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6980. Min Act: -0.1700

Data Index: 3448802 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6751. Min Act: -0.1700

Data Index: 8069992 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6521. Min Act: -0.1700

Data Index: 177592 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6436. Min Act: -0.1700

Data Index: 4112005 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6065. Min Act: -0.1700

Data Index: 5929159 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6113. Min Act: -0.1700

Data Index: 7743270 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6139. Min Act: -0.1700

Data Index: 314426 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.6077. Min Act: -0.1700

Data Index: 2865274 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.5805. Min Act: -0.1700

Data Index: 4136274 (Open Web Text)

Max Activating Token Index: 925

Text #19

Max Range: 3.9953. Min Range: -3.9953

Max Act: 3.5899. Min Act: -0.1700

Data Index: 4164718 (Open Web Text)

Max Activating Token Index: 253