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

Dataset: Open Web Text

Neuron 884 in Layer 4

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: 3.4856. Min Range: -3.4856

Max Act: 3.4856. Min Act: -0.1700

Data Index: 7928134 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4103. Min Act: -0.1700

Data Index: 6562844 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4384. Min Act: -0.1700

Data Index: 3718864 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3990. Min Act: -0.1700

Data Index: 816364 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3799. Min Act: -0.1700

Data Index: 4551113 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3189. Min Act: -0.1700

Data Index: 8251477 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3574. Min Act: -0.1700

Data Index: 6321854 (Open Web Text)

Max Activating Token Index: 790

Text #7

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3540. Min Act: -0.1700

Data Index: 5454819 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3319. Min Act: -0.1700

Data Index: 8464347 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3249. Min Act: -0.1700

Data Index: 7011687 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3058. Min Act: -0.1700

Data Index: 4046888 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3478. Min Act: -0.1700

Data Index: 2898171 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3008. Min Act: -0.1700

Data Index: 8129655 (Open Web Text)

Max Activating Token Index: 607

Text #13

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3511. Min Act: -0.1700

Data Index: 2694098 (Open Web Text)

Max Activating Token Index: 691

Text #14

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3408. Min Act: -0.1700

Data Index: 8824057 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.2834. Min Act: -0.1700

Data Index: 5047595 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3141. Min Act: -0.1700

Data Index: 5044582 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3094. Min Act: -0.1700

Data Index: 3479654 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.2294. Min Act: -0.1700

Data Index: 1199015 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.2585. Min Act: -0.1700

Data Index: 1665155 (Open Web Text)

Max Activating Token Index: 956