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

Dataset: Open Web Text

Neuron 1861 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: 4.1153. Min Range: -4.1153

Max Act: 4.1153. Min Act: -0.1700

Data Index: 5845283 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 4.1153. Min Range: -4.1153

Max Act: 4.0300. Min Act: -0.1700

Data Index: 4882171 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 4.1153. Min Range: -4.1153

Max Act: 4.0267. Min Act: -0.1700

Data Index: 3830608 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.1153. Min Range: -4.1153

Max Act: 4.0437. Min Act: -0.1700

Data Index: 6555008 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 4.1153. Min Range: -4.1153

Max Act: 4.0428. Min Act: -0.1700

Data Index: 7016704 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 4.1153. Min Range: -4.1153

Max Act: 4.0246. Min Act: -0.1700

Data Index: 4324729 (Open Web Text)

Max Activating Token Index: 734

Text #6

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9808. Min Act: -0.1700

Data Index: 6782691 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9740. Min Act: -0.1700

Data Index: 725016 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9432. Min Act: -0.1700

Data Index: 6301007 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9584. Min Act: -0.1700

Data Index: 2742183 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9411. Min Act: -0.1700

Data Index: 5984547 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9620. Min Act: -0.1700

Data Index: 5640160 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9505. Min Act: -0.1700

Data Index: 4883626 (Open Web Text)

Max Activating Token Index: 694

Text #13

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9519. Min Act: -0.1700

Data Index: 2113842 (Open Web Text)

Max Activating Token Index: 888

Text #14

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9662. Min Act: -0.1700

Data Index: 1049619 (Open Web Text)

Max Activating Token Index: 818

Text #15

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9479. Min Act: -0.1700

Data Index: 3399420 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9614. Min Act: -0.1700

Data Index: 4797647 (Open Web Text)

Max Activating Token Index: 739

Text #17

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9489. Min Act: -0.1700

Data Index: 708267 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9404. Min Act: -0.1700

Data Index: 393786 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 4.1153. Min Range: -4.1153

Max Act: 3.9445. Min Act: -0.1700

Data Index: 8148916 (Open Web Text)

Max Activating Token Index: 537