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

Dataset: Open Web Text

Neuron 2915 in Layer 6

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: 3.3527. Min Range: -3.3527

Max Act: 3.3527. Min Act: -0.1700

Data Index: 6024448 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1516993 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.3040. Min Act: -0.1700

Data Index: 5118613 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2784. Min Act: -0.1700

Data Index: 8244225 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2752. Min Act: -0.1700

Data Index: 2583418 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2761. Min Act: -0.1700

Data Index: 2845758 (Open Web Text)

Max Activating Token Index: 789

Text #6

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2162. Min Act: -0.1700

Data Index: 371236 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2106. Min Act: -0.1700

Data Index: 4186741 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2154. Min Act: -0.1700

Data Index: 2972968 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2069. Min Act: -0.1700

Data Index: 3749658 (Open Web Text)

Max Activating Token Index: 900

Text #10

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2196. Min Act: -0.1700

Data Index: 5704822 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1924. Min Act: -0.1700

Data Index: 2989728 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1893. Min Act: -0.1700

Data Index: 4569294 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1984. Min Act: -0.1700

Data Index: 3798187 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1768. Min Act: -0.1700

Data Index: 3464667 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1676. Min Act: -0.1700

Data Index: 7787392 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1619. Min Act: -0.1700

Data Index: 7305771 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1755. Min Act: -0.1700

Data Index: 5151225 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1584. Min Act: -0.1700

Data Index: 3839432 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1686. Min Act: -0.1700

Data Index: 973233 (Open Web Text)

Max Activating Token Index: 120