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

Dataset: Open Web Text

Neuron 271 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: 3.7784. Min Range: -3.7784

Max Act: 3.7784. Min Act: -0.1700

Data Index: 8598361 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1541833 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.6816. Min Act: -0.1700

Data Index: 6312796 (Open Web Text)

Max Activating Token Index: 506

Text #3

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.6345. Min Act: -0.1700

Data Index: 8603871 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.6162. Min Act: -0.1700

Data Index: 6701861 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.5586. Min Act: -0.1700

Data Index: 8499600 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.4765. Min Act: -0.1700

Data Index: 8440183 (Open Web Text)

Max Activating Token Index: 894

Text #7

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.5894. Min Act: -0.1700

Data Index: 3804259 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.4968. Min Act: -0.1700

Data Index: 4044079 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.5053. Min Act: -0.1700

Data Index: 7727381 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.5071. Min Act: -0.1700

Data Index: 2018998 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.4049. Min Act: -0.1700

Data Index: 1004719 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3967. Min Act: -0.1700

Data Index: 4592107 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3762. Min Act: -0.1700

Data Index: 3817209 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.4476. Min Act: -0.1700

Data Index: 8454025 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.4170. Min Act: -0.1700

Data Index: 5543123 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3789. Min Act: -0.1700

Data Index: 2848515 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3488. Min Act: -0.1700

Data Index: 5109447 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3059. Min Act: -0.1700

Data Index: 7835787 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 3.7784. Min Range: -3.7784

Max Act: 3.3335. Min Act: -0.1700

Data Index: 8051465 (Open Web Text)

Max Activating Token Index: 288