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

Dataset: Open Web Text

Neuron 2735 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: 5.5053. Min Range: -5.5053

Max Act: 5.5053. Min Act: -0.1700

Data Index: 5332903 (Open Web Text)

Max Activating Token Index: 818

Text #1

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4914. Min Act: -0.1700

Data Index: 7436055 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4451. Min Act: -0.1700

Data Index: 5719351 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4458. Min Act: -0.1700

Data Index: 7030789 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4356. Min Act: -0.1700

Data Index: 5719373 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3700. Min Act: -0.1700

Data Index: 6652033 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4273. Min Act: -0.1700

Data Index: 7530253 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3143. Min Act: -0.1700

Data Index: 2119531 (Open Web Text)

Max Activating Token Index: 728

Text #8

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3730. Min Act: -0.1700

Data Index: 7878529 (Open Web Text)

Max Activating Token Index: 666

Text #9

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3451. Min Act: -0.1700

Data Index: 3045489 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3051. Min Act: -0.1700

Data Index: 273881 (Open Web Text)

Max Activating Token Index: 939

Text #11

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2886. Min Act: -0.1700

Data Index: 8634844 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2410. Min Act: -0.1700

Data Index: 6810290 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2728. Min Act: -0.1700

Data Index: 4574895 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2566. Min Act: -0.1700

Data Index: 6555141 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2734. Min Act: -0.1700

Data Index: 4375784 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2862. Min Act: -0.1700

Data Index: 7685778 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2524. Min Act: -0.1700

Data Index: 295137 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2172. Min Act: -0.1700

Data Index: 6404471 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2303. Min Act: -0.1700

Data Index: 4195802 (Open Web Text)

Max Activating Token Index: 531