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

Dataset: Open Web Text

Neuron 2082 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: 4.8552. Min Range: -4.8552

Max Act: 4.8552. Min Act: -0.1700

Data Index: 4357760 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.7716. Min Act: -0.1700

Data Index: 4211012 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.7230. Min Act: -0.1700

Data Index: 1977447 (Open Web Text)

Max Activating Token Index: 577

Text #3

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.7185. Min Act: -0.1700

Data Index: 6733812 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.6322. Min Act: -0.1700

Data Index: 5685420 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.6661. Min Act: -0.1700

Data Index: 1154496 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5964. Min Act: -0.1700

Data Index: 5423129 (Open Web Text)

Max Activating Token Index: 585

Text #7

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.6050. Min Act: -0.1700

Data Index: 463809 (Open Web Text)

Max Activating Token Index: 924

Text #8

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5635. Min Act: -0.1700

Data Index: 5252286 (Open Web Text)

Max Activating Token Index: 766

Text #9

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5630. Min Act: -0.1700

Data Index: 6571 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5729. Min Act: -0.1700

Data Index: 958653 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5163. Min Act: -0.1700

Data Index: 2741330 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5130. Min Act: -0.1700

Data Index: 4870202 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5627. Min Act: -0.1700

Data Index: 497237 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5266. Min Act: -0.1700

Data Index: 6791681 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5250. Min Act: -0.1700

Data Index: 3369701 (Open Web Text)

Max Activating Token Index: 828

Text #16

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5281. Min Act: -0.1700

Data Index: 2207596 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.4910. Min Act: -0.1700

Data Index: 4503573 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.5183. Min Act: -0.1700

Data Index: 3801826 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 4.8552. Min Range: -4.8552

Max Act: 4.4786. Min Act: -0.1700

Data Index: 4457822 (Open Web Text)

Max Activating Token Index: 509