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

Dataset: Open Web Text

Neuron 668 in Layer 5

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: 5.4883. Min Range: -5.4883

Max Act: 5.4883. Min Act: -0.1700

Data Index: 7542112 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.3133. Min Act: -0.1700

Data Index: 7974156 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.3170. Min Act: -0.1700

Data Index: 2268037 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1441937 (Open Web Text)

Max Activating Token Index: 958

Text #4

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2472. Min Act: -0.1700

Data Index: 2494014 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2024. Min Act: -0.1700

Data Index: 3315033 (Open Web Text)

Max Activating Token Index: 373

Text #6

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2080. Min Act: -0.1700

Data Index: 5725513 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2022. Min Act: -0.1700

Data Index: 4368083 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2363. Min Act: -0.1700

Data Index: 3261619 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1774. Min Act: -0.1700

Data Index: 7341561 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1873. Min Act: -0.1700

Data Index: 1034906 (Open Web Text)

Max Activating Token Index: 889

Text #11

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.2055. Min Act: -0.1700

Data Index: 7173925 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1241. Min Act: -0.1700

Data Index: 7192061 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1652. Min Act: -0.1700

Data Index: 3355596 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1756. Min Act: -0.1700

Data Index: 7437955 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1045. Min Act: -0.1700

Data Index: 6787029 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1461. Min Act: -0.1700

Data Index: 2368515 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1330. Min Act: -0.1700

Data Index: 145652 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.0967. Min Act: -0.1700

Data Index: 618857 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 5.4883. Min Range: -5.4883

Max Act: 5.1366. Min Act: -0.1700

Data Index: 422143 (Open Web Text)

Max Activating Token Index: 37