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

Dataset: Open Web Text

Neuron 889 in Layer 3

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: 6.3292. Min Range: -6.3292

Max Act: 6.3292. Min Act: -0.1700

Data Index: 3148208 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2430. Min Act: -0.1700

Data Index: 7422286 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2700. Min Act: -0.1700

Data Index: 4087417 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2393. Min Act: -0.1700

Data Index: 311318 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2516. Min Act: -0.1700

Data Index: 6849755 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2618. Min Act: -0.1700

Data Index: 1479201 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2147. Min Act: -0.1700

Data Index: 5993416 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2582. Min Act: -0.1700

Data Index: 1407957 (Open Web Text)

Max Activating Token Index: 776

Text #8

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2455. Min Act: -0.1700

Data Index: 8224159 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2086. Min Act: -0.1694

Data Index: 431818 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.1997. Min Act: -0.1700

Data Index: 1234442 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2360. Min Act: -0.1700

Data Index: 3012646 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.1789. Min Act: -0.1700

Data Index: 2938831 (Open Web Text)

Max Activating Token Index: 143

Text #13

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.1837. Min Act: -0.1700

Data Index: 6269826 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2214. Min Act: -0.1700

Data Index: 6513873 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2038. Min Act: -0.1700

Data Index: 4795248 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2213. Min Act: -0.1700

Data Index: 4720944 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2102. Min Act: -0.1700

Data Index: 7114740 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.2018. Min Act: -0.1700

Data Index: 7173843 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 6.3292. Min Range: -6.3292

Max Act: 6.1862. Min Act: -0.1700

Data Index: 2405965 (Open Web Text)

Max Activating Token Index: 178