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

Dataset: Open Web Text

Neuron 2496 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: 3.7670. Min Range: -3.7670

Max Act: 3.7670. Min Act: -0.1700

Data Index: 1923626 (Open Web Text)

Max Activating Token Index: 275

Text #1

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6810. Min Act: -0.1700

Data Index: 2633491 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6904. Min Act: -0.1700

Data Index: 4331129 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6090. Min Act: -0.1700

Data Index: 6123942 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5922. Min Act: -0.1700

Data Index: 1943667 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5584. Min Act: -0.1700

Data Index: 4569496 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5673. Min Act: -0.1700

Data Index: 4549768 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5926. Min Act: -0.1700

Data Index: 2779656 (Open Web Text)

Max Activating Token Index: 452

Text #8

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5937. Min Act: -0.1700

Data Index: 6824859 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5881. Min Act: -0.1700

Data Index: 2448563 (Open Web Text)

Max Activating Token Index: 539

Text #10

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5880. Min Act: -0.1700

Data Index: 33240 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5772. Min Act: -0.1700

Data Index: 4569494 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1693385 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5687. Min Act: -0.1700

Data Index: 461212 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5475. Min Act: -0.1700

Data Index: 565950 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5100. Min Act: -0.1700

Data Index: 948048 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5037. Min Act: -0.1700

Data Index: 3928753 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5327. Min Act: -0.1700

Data Index: 7046764 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5040. Min Act: -0.1700

Data Index: 5434012 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.5329. Min Act: -0.1700

Data Index: 280839 (Open Web Text)

Max Activating Token Index: 284