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

Dataset: Open Web Text

Neuron 358 in Layer 0

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: 3.3819. Min Range: -3.3819

Max Act: 3.3819. Min Act: -0.1700

Data Index: 8385707 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3372. Min Act: -0.1700

Data Index: 6230901 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3358. Min Act: -0.1700

Data Index: 4253066 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3685. Min Act: -0.1700

Data Index: 2999571 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3364. Min Act: -0.1700

Data Index: 3638845 (Open Web Text)

Max Activating Token Index: 710

Text #5

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3064. Min Act: -0.1700

Data Index: 6411193 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1076738 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3161. Min Act: -0.1700

Data Index: 5964416 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3138. Min Act: -0.1700

Data Index: 2826309 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3377. Min Act: -0.1700

Data Index: 1988718 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2981. Min Act: -0.1700

Data Index: 8407280 (Open Web Text)

Max Activating Token Index: 764

Text #11

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3132. Min Act: -0.1700

Data Index: 6909049 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3012. Min Act: -0.1700

Data Index: 6172415 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2889. Min Act: -0.1700

Data Index: 5107728 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2752. Min Act: -0.1700

Data Index: 1668761 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3003. Min Act: -0.1700

Data Index: 7052307 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2506. Min Act: -0.1700

Data Index: 5870766 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2619. Min Act: -0.1700

Data Index: 5413409 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2550. Min Act: -0.1700

Data Index: 1560490 (Open Web Text)

Max Activating Token Index: 483

Text #19

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2722. Min Act: -0.1700

Data Index: 387615 (Open Web Text)

Max Activating Token Index: 6