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

Dataset: Open Web Text

Neuron 2799 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: 4.5876. Min Range: -4.5876

Max Act: 4.5876. Min Act: -0.1700

Data Index: 1365231 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.5152. Min Act: -0.1700

Data Index: 7009212 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.5153. Min Act: -0.1700

Data Index: 6664815 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.4879. Min Act: -0.1700

Data Index: 5170119 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.4401. Min Act: -0.1700

Data Index: 3443228 (Open Web Text)

Max Activating Token Index: 488

Text #5

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.4045. Min Act: -0.1700

Data Index: 5110425 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.3097. Min Act: -0.1700

Data Index: 7237545 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.3213. Min Act: -0.1700

Data Index: 5959203 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.3559. Min Act: -0.1700

Data Index: 4270502 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.3447. Min Act: -0.1700

Data Index: 604372 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.3090. Min Act: -0.1700

Data Index: 278404 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2919. Min Act: -0.1700

Data Index: 6426201 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2827. Min Act: -0.1700

Data Index: 2942054 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2433. Min Act: -0.1700

Data Index: 3164025 (Open Web Text)

Max Activating Token Index: 994

Text #14

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2509. Min Act: -0.1700

Data Index: 6612438 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2653. Min Act: -0.1700

Data Index: 252256 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2523. Min Act: -0.1700

Data Index: 6589159 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2337. Min Act: -0.1700

Data Index: 1727429 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2486. Min Act: -0.1700

Data Index: 4379763 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 4.5876. Min Range: -4.5876

Max Act: 4.2497. Min Act: -0.1700

Data Index: 4889084 (Open Web Text)

Max Activating Token Index: 300