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

Dataset: Open Web Text

Neuron 340 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: 3.3815. Min Range: -3.3815

Max Act: 3.3815. Min Act: -0.1700

Data Index: 3951451 (Open Web Text)

Max Activating Token Index: 492

Text #1

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.3418. Min Act: -0.1700

Data Index: 5140344 (Open Web Text)

Max Activating Token Index: 798

Text #2

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.3200. Min Act: -0.1700

Data Index: 2130826 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.3267. Min Act: -0.1700

Data Index: 6495783 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.3091. Min Act: -0.1700

Data Index: 5931629 (Open Web Text)

Max Activating Token Index: 85

Text #5

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.3381. Min Act: -0.1700

Data Index: 146168 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2584. Min Act: -0.1700

Data Index: 3516873 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2529. Min Act: -0.1700

Data Index: 5562540 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2440. Min Act: -0.1700

Data Index: 811453 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2311. Min Act: -0.1700

Data Index: 8232245 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2773. Min Act: -0.1700

Data Index: 2623850 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2532. Min Act: -0.1700

Data Index: 4498796 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.1998. Min Act: -0.1700

Data Index: 2327054 (Open Web Text)

Max Activating Token Index: 812

Text #13

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2158. Min Act: -0.1700

Data Index: 4800306 (Open Web Text)

Max Activating Token Index: 845

Text #14

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2009. Min Act: -0.1700

Data Index: 5255551 (Open Web Text)

Max Activating Token Index: 147

Text #15

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2230. Min Act: -0.1700

Data Index: 6856280 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2186. Min Act: -0.1700

Data Index: 2362829 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.1916. Min Act: -0.1700

Data Index: 5302515 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.2011. Min Act: -0.1700

Data Index: 2423236 (Open Web Text)

Max Activating Token Index: 723

Text #19

Max Range: 3.3815. Min Range: -3.3815

Max Act: 3.1899. Min Act: -0.1700

Data Index: 737378 (Open Web Text)

Max Activating Token Index: 287