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

Dataset: Open Web Text

Neuron 1437 in Layer 2

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: 4.7654. Min Range: -4.7654

Max Act: 4.7654. Min Act: -0.1700

Data Index: 6650531 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.6871. Min Act: -0.1700

Data Index: 3988606 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.6169. Min Act: -0.1700

Data Index: 1109653 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.6058. Min Act: -0.1700

Data Index: 6601406 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.5465. Min Act: -0.1700

Data Index: 7568900 (Open Web Text)

Max Activating Token Index: 896

Text #5

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.5467. Min Act: -0.1700

Data Index: 3772379 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.5144. Min Act: -0.1700

Data Index: 2501043 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.5085. Min Act: -0.1700

Data Index: 8582676 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4856. Min Act: -0.1700

Data Index: 2340590 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.5098. Min Act: -0.1700

Data Index: 2070843 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4777. Min Act: -0.1700

Data Index: 2179064 (Open Web Text)

Max Activating Token Index: 986

Text #11

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4882. Min Act: -0.1700

Data Index: 1201465 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4657. Min Act: -0.1700

Data Index: 8254368 (Open Web Text)

Max Activating Token Index: 359

Text #13

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4131. Min Act: -0.1700

Data Index: 7726974 (Open Web Text)

Max Activating Token Index: 728

Text #14

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4412. Min Act: -0.1700

Data Index: 8290281 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4513. Min Act: -0.1700

Data Index: 2607331 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4316. Min Act: -0.1700

Data Index: 3295997 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4535. Min Act: -0.1700

Data Index: 5331411 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4353. Min Act: -0.1700

Data Index: 8144089 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 4.7654. Min Range: -4.7654

Max Act: 4.4453. Min Act: -0.1700

Data Index: 5037391 (Open Web Text)

Max Activating Token Index: 304