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

Dataset: Open Web Text

Neuron 2010 in Layer 1

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: 1.7853. Min Range: -1.7853

Max Act: 1.7853. Min Act: -0.1700

Data Index: 7947033 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7638. Min Act: -0.1700

Data Index: 3678097 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7408. Min Act: -0.1700

Data Index: 8490617 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7283. Min Act: -0.1700

Data Index: 2668035 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7056. Min Act: -0.1700

Data Index: 3279621 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7088. Min Act: -0.1700

Data Index: 3116741 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7087. Min Act: -0.1700

Data Index: 2412716 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7082. Min Act: -0.1700

Data Index: 3648619 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7140. Min Act: -0.1699

Data Index: 6263333 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7056. Min Act: -0.1699

Data Index: 562982 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7047. Min Act: -0.1700

Data Index: 6563929 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7078. Min Act: -0.1700

Data Index: 7741718 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6925. Min Act: -0.1700

Data Index: 4302305 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6926. Min Act: -0.1700

Data Index: 2153265 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6856. Min Act: -0.1700

Data Index: 5952256 (Open Web Text)

Max Activating Token Index: 490

Text #15

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6882. Min Act: -0.1692

Data Index: 6510351 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6875. Min Act: -0.1700

Data Index: 1388067 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6737. Min Act: -0.1700

Data Index: 2817168 (Open Web Text)

Max Activating Token Index: 259

Text #18

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6822. Min Act: -0.1700

Data Index: 2571142 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6760. Min Act: -0.1700

Data Index: 5350165 (Open Web Text)

Max Activating Token Index: 327