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

Dataset: Open Web Text

Neuron 1929 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: 4.3994. Min Range: -4.3994

Max Act: 4.3994. Min Act: -0.1700

Data Index: 2181078 (Open Web Text)

Max Activating Token Index: 711

Text #1

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.1619. Min Act: -0.1700

Data Index: 415002 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.1468. Min Act: -0.1700

Data Index: 263606 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.0333. Min Act: -0.1700

Data Index: 3025648 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.0060. Min Act: -0.1700

Data Index: 7323932 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.0179. Min Act: -0.1700

Data Index: 2836111 (Open Web Text)

Max Activating Token Index: 136

Text #6

Max Range: 4.3994. Min Range: -4.3994

Max Act: 4.0091. Min Act: -0.1700

Data Index: 8751082 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9863. Min Act: -0.1700

Data Index: 5478050 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9687. Min Act: -0.1700

Data Index: 5400350 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9472. Min Act: -0.1700

Data Index: 8325927 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9559. Min Act: -0.1700

Data Index: 2964321 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9424. Min Act: -0.1700

Data Index: 7716932 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9451. Min Act: -0.1700

Data Index: 8571964 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9191. Min Act: -0.1700

Data Index: 4605172 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9505. Min Act: -0.1700

Data Index: 7128206 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9272. Min Act: -0.1700

Data Index: 3155680 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9277. Min Act: -0.1700

Data Index: 2293098 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.9135. Min Act: -0.1700

Data Index: 5673759 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.8914. Min Act: -0.1700

Data Index: 1722688 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 4.3994. Min Range: -4.3994

Max Act: 3.8951. Min Act: -0.1700

Data Index: 6332536 (Open Web Text)

Max Activating Token Index: 492