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

Dataset: Open Web Text

Neuron 2134 in Layer 6

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: 4.3929. Min Range: -4.3929

Max Act: 4.3929. Min Act: -0.1700

Data Index: 7892759 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.3928. Min Act: -0.1700

Data Index: 3273400 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.3388. Min Act: -0.1700

Data Index: 1487063 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.2738. Min Act: -0.1700

Data Index: 934618 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.2339. Min Act: -0.1700

Data Index: 1487064 (Open Web Text)

Max Activating Token Index: 217

Text #5

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1866. Min Act: -0.1700

Data Index: 1044631 (Open Web Text)

Max Activating Token Index: 855

Text #6

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1958. Min Act: -0.1700

Data Index: 8099774 (Open Web Text)

Max Activating Token Index: 693

Text #7

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1821. Min Act: -0.1700

Data Index: 1473189 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1883. Min Act: -0.1700

Data Index: 6611071 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1637. Min Act: -0.1700

Data Index: 7892761 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1399. Min Act: -0.1700

Data Index: 8573150 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1405. Min Act: -0.1700

Data Index: 1943338 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1171. Min Act: -0.1700

Data Index: 7017456 (Open Web Text)

Max Activating Token Index: 66

Text #13

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1217. Min Act: -0.1700

Data Index: 4961926 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1135. Min Act: -0.1700

Data Index: 7587754 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.1270. Min Act: -0.1700

Data Index: 3209082 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.0771. Min Act: -0.1700

Data Index: 4411834 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.0767. Min Act: -0.1700

Data Index: 867878 (Open Web Text)

Max Activating Token Index: 372

Text #18

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.0723. Min Act: -0.1700

Data Index: 1355101 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 4.3929. Min Range: -4.3929

Max Act: 4.0695. Min Act: -0.1700

Data Index: 5416821 (Open Web Text)

Max Activating Token Index: 810