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

Dataset: Open Web Text

Neuron 1016 in Layer 3

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: 4.3093. Min Range: -4.3093

Max Act: 4.3093. Min Act: -0.1700

Data Index: 7392287 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.1141. Min Act: -0.1700

Data Index: 4333290 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.0911. Min Act: -0.1700

Data Index: 5662098 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.0552. Min Act: -0.1700

Data Index: 3800398 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.0436. Min Act: -0.1700

Data Index: 4664534 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.0173. Min Act: -0.1700

Data Index: 1400822 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9892. Min Act: -0.1700

Data Index: 274317 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 4.3093. Min Range: -4.3093

Max Act: 4.0140. Min Act: -0.1700

Data Index: 2023623 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9717. Min Act: -0.1700

Data Index: 1400460 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9600. Min Act: -0.1700

Data Index: 6747141 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9746. Min Act: -0.1700

Data Index: 981279 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9572. Min Act: -0.1700

Data Index: 8145663 (Open Web Text)

Max Activating Token Index: 193

Text #12

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9339. Min Act: -0.1700

Data Index: 274316 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9264. Min Act: -0.1700

Data Index: 8155070 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9567. Min Act: -0.1700

Data Index: 8643552 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9550. Min Act: -0.1700

Data Index: 8726819 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9551. Min Act: -0.1700

Data Index: 6257933 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9322. Min Act: -0.1700

Data Index: 4924967 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.8909. Min Act: -0.1700

Data Index: 4914698 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 4.3093. Min Range: -4.3093

Max Act: 3.9052. Min Act: -0.1700

Data Index: 6824570 (Open Web Text)

Max Activating Token Index: 804