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

Dataset: Open Web Text

Neuron 852 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: 5.2943. Min Range: -5.2943

Max Act: 5.2943. Min Act: -0.1700

Data Index: 491403 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.9653. Min Act: -0.1700

Data Index: 780983 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.9108. Min Act: -0.1700

Data Index: 5457811 (Open Web Text)

Max Activating Token Index: 104

Text #3

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8649. Min Act: -0.1700

Data Index: 3709846 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8777. Min Act: -0.1700

Data Index: 7705225 (Open Web Text)

Max Activating Token Index: 937

Text #5

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8938. Min Act: -0.1700

Data Index: 4601809 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8291. Min Act: -0.1700

Data Index: 91398 (Open Web Text)

Max Activating Token Index: 790

Text #7

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8395. Min Act: -0.1700

Data Index: 1593062 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8391. Min Act: -0.1700

Data Index: 1506541 (Open Web Text)

Max Activating Token Index: 252

Text #9

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8701. Min Act: -0.1700

Data Index: 2315338 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8430. Min Act: -0.1700

Data Index: 3405900 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8245. Min Act: -0.1700

Data Index: 6531652 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8406. Min Act: -0.1700

Data Index: 3232353 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8492. Min Act: -0.1700

Data Index: 5912479 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8481. Min Act: -0.1700

Data Index: 4827483 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8086. Min Act: -0.1700

Data Index: 2258723 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8012. Min Act: -0.1700

Data Index: 3557706 (Open Web Text)

Max Activating Token Index: 141

Text #17

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8128. Min Act: -0.1700

Data Index: 3647234 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8125. Min Act: -0.1700

Data Index: 4142041 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 5.2943. Min Range: -5.2943

Max Act: 4.8200. Min Act: -0.1700

Data Index: 1077988 (Open Web Text)

Max Activating Token Index: 260