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

Dataset: Open Web Text

Neuron 2782 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: 4.4073. Min Range: -4.4073

Max Act: 4.4073. Min Act: -0.1700

Data Index: 2155602 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3798. Min Act: -0.1700

Data Index: 7213776 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.4047. Min Act: -0.1700

Data Index: 6296794 (Open Web Text)

Max Activating Token Index: 305

Text #3

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3696. Min Act: -0.1700

Data Index: 4113304 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3727. Min Act: -0.1700

Data Index: 4273280 (Open Web Text)

Max Activating Token Index: 622

Text #5

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3795. Min Act: -0.1700

Data Index: 868364 (Open Web Text)

Max Activating Token Index: 102

Text #6

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3676. Min Act: -0.1700

Data Index: 4888632 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3972. Min Act: -0.1700

Data Index: 4918145 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3341. Min Act: -0.1700

Data Index: 607959 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3486. Min Act: -0.1700

Data Index: 6969140 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3218. Min Act: -0.1700

Data Index: 2552492 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3173. Min Act: -0.1700

Data Index: 6750108 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3034. Min Act: -0.1700

Data Index: 8771476 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.2884. Min Act: -0.1700

Data Index: 626727 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.2887. Min Act: -0.1700

Data Index: 2871647 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.2844. Min Act: -0.1700

Data Index: 2502498 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3035. Min Act: -0.1700

Data Index: 4739319 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3116. Min Act: -0.1700

Data Index: 4505970 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.2999. Min Act: -0.1700

Data Index: 4302539 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 4.4073. Min Range: -4.4073

Max Act: 4.3288. Min Act: -0.1700

Data Index: 4248003 (Open Web Text)

Max Activating Token Index: 532