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

Dataset: Open Web Text

Neuron 2705 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: 4.5099. Min Range: -4.5099

Max Act: 4.5099. Min Act: -0.1700

Data Index: 7785956 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4047. Min Act: -0.1700

Data Index: 41045 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4349. Min Act: -0.1700

Data Index: 8188319 (Open Web Text)

Max Activating Token Index: 842

Text #3

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4370. Min Act: -0.1700

Data Index: 4162531 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3977. Min Act: -0.1700

Data Index: 7653702 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3812. Min Act: -0.1700

Data Index: 550626 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3919. Min Act: -0.1700

Data Index: 7113789 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4041. Min Act: -0.1700

Data Index: 6010182 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3975. Min Act: -0.1700

Data Index: 1560850 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4066. Min Act: -0.1700

Data Index: 5692398 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.4115. Min Act: -0.1700

Data Index: 3266340 (Open Web Text)

Max Activating Token Index: 153

Text #11

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3975. Min Act: -0.1700

Data Index: 8396080 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3599. Min Act: -0.1700

Data Index: 2068162 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3490. Min Act: -0.1700

Data Index: 2574638 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3700. Min Act: -0.1700

Data Index: 5693214 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3744. Min Act: -0.1700

Data Index: 1426910 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3635. Min Act: -0.1700

Data Index: 2986729 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3539. Min Act: -0.1700

Data Index: 5789302 (Open Web Text)

Max Activating Token Index: 961

Text #18

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3505. Min Act: -0.1700

Data Index: 5202745 (Open Web Text)

Max Activating Token Index: 923

Text #19

Max Range: 4.5099. Min Range: -4.5099

Max Act: 4.3470. Min Act: -0.1700

Data Index: 3469975 (Open Web Text)

Max Activating Token Index: 50