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

Dataset: Open Web Text

Neuron 988 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: 3.5678. Min Range: -3.5678

Max Act: 3.5540. Min Act: -0.1700

Data Index: 8099768 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5678. Min Act: -0.1700

Data Index: 3446717 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5474. Min Act: -0.1700

Data Index: 2127245 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5477. Min Act: -0.1700

Data Index: 3752462 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5167. Min Act: -0.1700

Data Index: 7104622 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4953. Min Act: -0.1700

Data Index: 5518669 (Open Web Text)

Max Activating Token Index: 62

Text #6

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5143. Min Act: -0.1700

Data Index: 512543 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5124. Min Act: -0.1700

Data Index: 3851732 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5196. Min Act: -0.1700

Data Index: 325480 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5116. Min Act: -0.1700

Data Index: 4740874 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5033. Min Act: -0.1700

Data Index: 7646992 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4949. Min Act: -0.1700

Data Index: 6920944 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4953. Min Act: -0.1700

Data Index: 5670008 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.5224. Min Act: -0.1700

Data Index: 4145222 (Open Web Text)

Max Activating Token Index: 208

Text #14

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4914. Min Act: -0.1700

Data Index: 2559411 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4544. Min Act: -0.1700

Data Index: 1711240 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4817. Min Act: -0.1700

Data Index: 1796220 (Open Web Text)

Max Activating Token Index: 248

Text #17

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4608. Min Act: -0.1700

Data Index: 4834283 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4747. Min Act: -0.1700

Data Index: 326355 (Open Web Text)

Max Activating Token Index: 786

Text #19

Max Range: 3.5678. Min Range: -3.5678

Max Act: 3.4625. Min Act: -0.1700

Data Index: 2186427 (Open Web Text)

Max Activating Token Index: 829