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

Dataset: Open Web Text

Neuron 2553 in Layer 4

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: 4.9917. Min Range: -4.9917

Max Act: 4.9917. Min Act: -0.1700

Data Index: 7376217 (Open Web Text)

Max Activating Token Index: 131

Text #1

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8647. Min Act: -0.1700

Data Index: 2648724 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8076. Min Act: -0.1700

Data Index: 6038257 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.8315. Min Act: -0.1700

Data Index: 7632756 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7673. Min Act: -0.1700

Data Index: 7289058 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7158. Min Act: -0.1700

Data Index: 6814542 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7591. Min Act: -0.1700

Data Index: 4235697 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.7256. Min Act: -0.1700

Data Index: 139792 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6818. Min Act: -0.1700

Data Index: 8530936 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6830. Min Act: -0.1700

Data Index: 7534991 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6366. Min Act: -0.1700

Data Index: 6352802 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6777. Min Act: -0.1700

Data Index: 3699496 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6715. Min Act: -0.1700

Data Index: 8661120 (Open Web Text)

Max Activating Token Index: 990

Text #13

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6584. Min Act: -0.1700

Data Index: 5179085 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6514. Min Act: -0.1700

Data Index: 3105891 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6301. Min Act: -0.1700

Data Index: 5695087 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6067. Min Act: -0.1700

Data Index: 6979684 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.5996. Min Act: -0.1700

Data Index: 178617 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.5427. Min Act: -0.1700

Data Index: 1248224 (Open Web Text)

Max Activating Token Index: 885

Text #19

Max Range: 4.9917. Min Range: -4.9917

Max Act: 4.6322. Min Act: -0.1700

Data Index: 662992 (Open Web Text)

Max Activating Token Index: 828