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

Dataset: Open Web Text

Neuron 918 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: 4.0199. Min Range: -4.0199

Max Act: 4.0199. Min Act: -0.1700

Data Index: 139980 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8382. Min Act: -0.1700

Data Index: 4395256 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7796. Min Act: -0.1700

Data Index: 1553544 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7647. Min Act: -0.1700

Data Index: 7530473 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7284. Min Act: -0.1700

Data Index: 2507184 (Open Web Text)

Max Activating Token Index: 351

Text #5

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7880. Min Act: -0.1700

Data Index: 3779702 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7099. Min Act: -0.1700

Data Index: 224553 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7536. Min Act: -0.1700

Data Index: 4261180 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6932. Min Act: -0.1700

Data Index: 1431290 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6950. Min Act: -0.1700

Data Index: 1814996 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7329. Min Act: -0.1700

Data Index: 5672967 (Open Web Text)

Max Activating Token Index: 330

Text #11

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6977. Min Act: -0.1700

Data Index: 4905516 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7119. Min Act: -0.1700

Data Index: 4860711 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7264. Min Act: -0.1700

Data Index: 8458989 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6938. Min Act: -0.1700

Data Index: 1045375 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6708. Min Act: -0.1700

Data Index: 5017638 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6806. Min Act: -0.1700

Data Index: 8346816 (Open Web Text)

Max Activating Token Index: 946

Text #17

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6571. Min Act: -0.1700

Data Index: 697494 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6765. Min Act: -0.1700

Data Index: 5172626 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.6644. Min Act: -0.1700

Data Index: 2493502 (Open Web Text)

Max Activating Token Index: 23