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

Dataset: Open Web Text

Neuron 1109 in Layer 6

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: 2.5402. Min Range: -2.5402

Max Act: 2.5402. Min Act: -0.1700

Data Index: 8629897 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.4505. Min Act: -0.1700

Data Index: 5920015 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.4476. Min Act: -0.1700

Data Index: 4941746 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.4477. Min Act: -0.1700

Data Index: 4446400 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3720. Min Act: -0.1700

Data Index: 2681619 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3108. Min Act: -0.1700

Data Index: 2291160 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3404. Min Act: -0.1700

Data Index: 6592407 (Open Web Text)

Max Activating Token Index: 798

Text #7

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3158. Min Act: -0.1700

Data Index: 2855646 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3531. Min Act: -0.1700

Data Index: 2479129 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3035. Min Act: -0.1700

Data Index: 4693210 (Open Web Text)

Max Activating Token Index: 119

Text #10

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3237. Min Act: -0.1700

Data Index: 4091903 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3076. Min Act: -0.1700

Data Index: 5832496 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.3150. Min Act: -0.1700

Data Index: 3580445 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2883. Min Act: -0.1700

Data Index: 2527037 (Open Web Text)

Max Activating Token Index: 879

Text #14

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2841. Min Act: -0.1700

Data Index: 3480272 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2530. Min Act: -0.1700

Data Index: 4182905 (Open Web Text)

Max Activating Token Index: 261

Text #16

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2893. Min Act: -0.1700

Data Index: 5724513 (Open Web Text)

Max Activating Token Index: 185

Text #17

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2694. Min Act: -0.1700

Data Index: 2137424 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2697. Min Act: -0.1700

Data Index: 1701111 (Open Web Text)

Max Activating Token Index: 328

Text #19

Max Range: 2.5402. Min Range: -2.5402

Max Act: 2.2667. Min Act: -0.1700

Data Index: 1834235 (Open Web Text)

Max Activating Token Index: 298