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

Dataset: Open Web Text

Neuron 2190 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: 2.7348. Min Range: -2.7348

Max Act: 2.7348. Min Act: -0.1700

Data Index: 6074488 (Open Web Text)

Max Activating Token Index: 253

Text #1

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.7096. Min Act: -0.1700

Data Index: 2827170 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.7046. Min Act: -0.1700

Data Index: 2861006 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.7043. Min Act: -0.1700

Data Index: 7688530 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6887. Min Act: -0.1700

Data Index: 5764247 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6757. Min Act: -0.1700

Data Index: 6548515 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6936. Min Act: -0.1700

Data Index: 4194786 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6771. Min Act: -0.1700

Data Index: 3546532 (Open Web Text)

Max Activating Token Index: 363

Text #8

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6816. Min Act: -0.1700

Data Index: 8432983 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6771. Min Act: -0.1700

Data Index: 1358252 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6710. Min Act: -0.1700

Data Index: 7887094 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6625. Min Act: -0.1700

Data Index: 2267568 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6636. Min Act: -0.1700

Data Index: 5494525 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6331. Min Act: -0.1700

Data Index: 3585675 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6429. Min Act: -0.1700

Data Index: 3042644 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6586. Min Act: -0.1700

Data Index: 656939 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6469. Min Act: -0.1700

Data Index: 2916638 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6461. Min Act: -0.1700

Data Index: 6342173 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6528. Min Act: -0.1700

Data Index: 1271455 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 2.7348. Min Range: -2.7348

Max Act: 2.6433. Min Act: -0.1700

Data Index: 4611903 (Open Web Text)

Max Activating Token Index: 104