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

Dataset: Open Web Text

Neuron 2413 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: 1.8976. Min Range: -1.8976

Max Act: 1.8976. Min Act: -0.1700

Data Index: 5222807 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8506. Min Act: -0.1700

Data Index: 2922005 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8461. Min Act: -0.1700

Data Index: 783547 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8515. Min Act: -0.1700

Data Index: 2495672 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8186. Min Act: -0.1700

Data Index: 5256474 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8163. Min Act: -0.1700

Data Index: 5143051 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7937. Min Act: -0.1700

Data Index: 5074024 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7799. Min Act: -0.1700

Data Index: 3163134 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.8051. Min Act: -0.1700

Data Index: 2127012 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7990. Min Act: -0.1700

Data Index: 1293795 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7719. Min Act: -0.1700

Data Index: 2406356 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7715. Min Act: -0.1700

Data Index: 4478251 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7871. Min Act: -0.1700

Data Index: 8645440 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7509. Min Act: -0.1700

Data Index: 5768128 (Open Web Text)

Max Activating Token Index: 229

Text #14

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7851. Min Act: -0.1700

Data Index: 2995065 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7600. Min Act: -0.1700

Data Index: 5727289 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7540. Min Act: -0.1700

Data Index: 4803417 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7674. Min Act: -0.1700

Data Index: 2100054 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7626. Min Act: -0.1700

Data Index: 1077415 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7388. Min Act: -0.1700

Data Index: 4466069 (Open Web Text)

Max Activating Token Index: 37