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

Dataset: Open Web Text

Neuron 9 in Layer 2

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: 4.3223. Min Range: -4.3223

Max Act: 4.3223. Min Act: -0.1700

Data Index: 5313645 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.2321. Min Act: -0.1700

Data Index: 3754045 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1515. Min Act: -0.1700

Data Index: 7143276 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1592. Min Act: -0.1700

Data Index: 3542907 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1508. Min Act: -0.1700

Data Index: 4050626 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1388. Min Act: -0.1700

Data Index: 1652929 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1003. Min Act: -0.1700

Data Index: 749452 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.1031. Min Act: -0.1700

Data Index: 7285248 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.0514. Min Act: -0.1700

Data Index: 1203120 (Open Web Text)

Max Activating Token Index: 957

Text #9

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.0229. Min Act: -0.1700

Data Index: 7997202 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.0116. Min Act: -0.1700

Data Index: 3708886 (Open Web Text)

Max Activating Token Index: 633

Text #11

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9925. Min Act: -0.1700

Data Index: 4803618 (Open Web Text)

Max Activating Token Index: 863

Text #12

Max Range: 4.3223. Min Range: -4.3223

Max Act: 4.0138. Min Act: -0.1700

Data Index: 3357706 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9899. Min Act: -0.1700

Data Index: 2521014 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9577. Min Act: -0.1700

Data Index: 7349827 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9551. Min Act: -0.1700

Data Index: 5180508 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9711. Min Act: -0.1700

Data Index: 6259187 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9436. Min Act: -0.1700

Data Index: 876137 (Open Web Text)

Max Activating Token Index: 854

Text #18

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9511. Min Act: -0.1700

Data Index: 1454935 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 4.3223. Min Range: -4.3223

Max Act: 3.9666. Min Act: -0.1700

Data Index: 7032420 (Open Web Text)

Max Activating Token Index: 840