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

Dataset: Open Web Text

Neuron 1983 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: 5.7471. Min Range: -5.7471

Max Act: 5.7471. Min Act: -0.1700

Data Index: 4082470 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.5958. Min Act: -0.1700

Data Index: 2958700 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.5438. Min Act: -0.1700

Data Index: 1671829 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4938. Min Act: -0.1700

Data Index: 4547175 (Open Web Text)

Max Activating Token Index: 888

Text #4

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4184. Min Act: -0.1700

Data Index: 3099482 (Open Web Text)

Max Activating Token Index: 472

Text #5

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4312. Min Act: -0.1700

Data Index: 7665942 (Open Web Text)

Max Activating Token Index: 749

Text #6

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4598. Min Act: -0.1700

Data Index: 3656652 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4051. Min Act: -0.1700

Data Index: 6295408 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4250. Min Act: -0.1700

Data Index: 1277717 (Open Web Text)

Max Activating Token Index: 832

Text #9

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3991. Min Act: -0.1700

Data Index: 7262057 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4139. Min Act: -0.1700

Data Index: 1003830 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3896. Min Act: -0.1700

Data Index: 5139635 (Open Web Text)

Max Activating Token Index: 886

Text #12

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3570. Min Act: -0.1700

Data Index: 3514927 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3551. Min Act: -0.1700

Data Index: 2680799 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3509. Min Act: -0.1700

Data Index: 346493 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.4106. Min Act: -0.1700

Data Index: 3804677 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3379. Min Act: -0.1700

Data Index: 1364000 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3319. Min Act: -0.1700

Data Index: 3039066 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3028. Min Act: -0.1700

Data Index: 461937 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 5.7471. Min Range: -5.7471

Max Act: 5.3711. Min Act: -0.1700

Data Index: 2074545 (Open Web Text)

Max Activating Token Index: 36