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

Dataset: Open Web Text

Neuron 248 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: 4.1202. Min Range: -4.1202

Max Act: 4.1202. Min Act: -0.1700

Data Index: 3893396 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.1202. Min Range: -4.1202

Max Act: 4.0649. Min Act: -0.1700

Data Index: 171210 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 4.1202. Min Range: -4.1202

Max Act: 4.0741. Min Act: -0.1700

Data Index: 7165094 (Open Web Text)

Max Activating Token Index: 262

Text #3

Max Range: 4.1202. Min Range: -4.1202

Max Act: 4.0370. Min Act: -0.1700

Data Index: 6520079 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.9495. Min Act: -0.1700

Data Index: 1383562 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8522. Min Act: -0.1700

Data Index: 6598164 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8121. Min Act: -0.1700

Data Index: 4629076 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8431. Min Act: -0.1700

Data Index: 1217989 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8052. Min Act: -0.1700

Data Index: 8193204 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.8098. Min Act: -0.1700

Data Index: 5729441 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7784. Min Act: -0.1700

Data Index: 5337318 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7621. Min Act: -0.1700

Data Index: 1983983 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7446. Min Act: -0.1700

Data Index: 5872517 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7242. Min Act: -0.1700

Data Index: 2193583 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7091. Min Act: -0.1700

Data Index: 2431493 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7671. Min Act: -0.1700

Data Index: 4869861 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7403. Min Act: -0.1700

Data Index: 5096933 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7391. Min Act: -0.1700

Data Index: 7178608 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7148. Min Act: -0.1700

Data Index: 7515076 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 4.1202. Min Range: -4.1202

Max Act: 3.7484. Min Act: -0.1700

Data Index: 3582539 (Open Web Text)

Max Activating Token Index: 512