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

Dataset: Open Web Text

Neuron 1626 in Layer 1

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: 1.9478. Min Range: -1.9478

Max Act: 1.9478. Min Act: -0.1700

Data Index: 953223 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.9203. Min Act: -0.1696

Data Index: 3401960 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7930. Min Act: -0.1700

Data Index: 8656715 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7634. Min Act: -0.1698

Data Index: 3401955 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7680. Min Act: -0.1698

Data Index: 3401964 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7631. Min Act: -0.1698

Data Index: 3401958 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7462. Min Act: -0.1700

Data Index: 3401957 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7496. Min Act: -0.1680

Data Index: 3401968 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7383. Min Act: -0.1691

Data Index: 3401961 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.7182. Min Act: -0.1700

Data Index: 2910261 (Open Web Text)

Max Activating Token Index: 89

Text #10

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6997. Min Act: -0.1700

Data Index: 3401954 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6980. Min Act: -0.1695

Data Index: 3401965 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6881. Min Act: -0.1698

Data Index: 3401962 (Open Web Text)

Max Activating Token Index: 299

Text #13

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6494. Min Act: -0.1700

Data Index: 6993529 (Open Web Text)

Max Activating Token Index: 891

Text #14

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6533. Min Act: -0.1700

Data Index: 7688460 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6490. Min Act: -0.1700

Data Index: 8437746 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6380. Min Act: -0.1700

Data Index: 6034663 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6365. Min Act: -0.1700

Data Index: 2993432 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6343. Min Act: -0.1700

Data Index: 5790328 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 1.9478. Min Range: -1.9478

Max Act: 1.6300. Min Act: -0.1700

Data Index: 2910271 (Open Web Text)

Max Activating Token Index: 66