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

Dataset: Open Web Text

Neuron 252 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: 3.3535. Min Range: -3.3535

Max Act: 3.3535. Min Act: -0.1700

Data Index: 819881 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.3211. Min Act: -0.1700

Data Index: 2929673 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2680. Min Act: -0.1700

Data Index: 320002 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2433. Min Act: -0.1700

Data Index: 7386111 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2450. Min Act: -0.1700

Data Index: 2352454 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2274. Min Act: -0.1700

Data Index: 3036776 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2195. Min Act: -0.1700

Data Index: 4357144 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2195. Min Act: -0.1700

Data Index: 4357145 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.2078. Min Act: -0.1700

Data Index: 4366312 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1982. Min Act: -0.1700

Data Index: 3143165 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1850. Min Act: -0.1700

Data Index: 5764069 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1464. Min Act: -0.1700

Data Index: 8536016 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1594. Min Act: -0.1700

Data Index: 3965163 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1435. Min Act: -0.1700

Data Index: 2510556 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1255. Min Act: -0.1700

Data Index: 5946371 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1269. Min Act: -0.1700

Data Index: 1146861 (Open Web Text)

Max Activating Token Index: 35

Text #16

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1115. Min Act: -0.1700

Data Index: 1456863 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1165. Min Act: -0.1700

Data Index: 4852779 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1150. Min Act: -0.1700

Data Index: 3973568 (Open Web Text)

Max Activating Token Index: 815

Text #19

Max Range: 3.3535. Min Range: -3.3535

Max Act: 3.1219. Min Act: -0.1700

Data Index: 6858234 (Open Web Text)

Max Activating Token Index: 7