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

Dataset: Open Web Text

Neuron 306 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: 4.5189. Min Range: -4.5189

Max Act: 4.5150. Min Act: -0.1700

Data Index: 6381402 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.5189. Min Act: -0.1700

Data Index: 6996082 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4682. Min Act: -0.1700

Data Index: 7199936 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4747. Min Act: -0.1700

Data Index: 8000974 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4488. Min Act: -0.1700

Data Index: 4393699 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4847. Min Act: -0.1700

Data Index: 7896566 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4567. Min Act: -0.1700

Data Index: 3939504 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3666. Min Act: -0.1700

Data Index: 4935872 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3847. Min Act: -0.1700

Data Index: 8052070 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3206. Min Act: -0.1700

Data Index: 6102254 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3380. Min Act: -0.1700

Data Index: 1431761 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3439. Min Act: -0.1700

Data Index: 7242325 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3303. Min Act: -0.1700

Data Index: 3825517 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3510. Min Act: -0.1700

Data Index: 1997923 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3544. Min Act: -0.1700

Data Index: 6698739 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3510. Min Act: -0.1700

Data Index: 6273237 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3176. Min Act: -0.1700

Data Index: 4417825 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3016. Min Act: -0.1700

Data Index: 4671559 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3062. Min Act: -0.1700

Data Index: 2971737 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.3092. Min Act: -0.1700

Data Index: 704697 (Open Web Text)

Max Activating Token Index: 12