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

Dataset: Open Web Text

Neuron 997 in Layer 4

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: 3.6032. Min Range: -3.6032

Max Act: 3.6032. Min Act: -0.1700

Data Index: 4281914 (Open Web Text)

Max Activating Token Index: 341

Text #1

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5818. Min Act: -0.1700

Data Index: 4869462 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5413. Min Act: -0.1700

Data Index: 2001963 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5007. Min Act: -0.1700

Data Index: 1375367 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5143. Min Act: -0.1700

Data Index: 938315 (Open Web Text)

Max Activating Token Index: 581

Text #5

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1411355 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.5033. Min Act: -0.1700

Data Index: 4036501 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4996. Min Act: -0.1700

Data Index: 29897 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4818. Min Act: -0.1700

Data Index: 828052 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1917716 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4796. Min Act: -0.1700

Data Index: 5628060 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4549. Min Act: -0.1700

Data Index: 5213126 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4371. Min Act: -0.1700

Data Index: 2426249 (Open Web Text)

Max Activating Token Index: 747

Text #13

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4957. Min Act: -0.1700

Data Index: 7197011 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4614. Min Act: -0.1700

Data Index: 8669235 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4382. Min Act: -0.1700

Data Index: 2805076 (Open Web Text)

Max Activating Token Index: 346

Text #16

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4626. Min Act: -0.1700

Data Index: 7513776 (Open Web Text)

Max Activating Token Index: 815

Text #17

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4352. Min Act: -0.1700

Data Index: 319583 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4454. Min Act: -0.1700

Data Index: 6599094 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 3.6032. Min Range: -3.6032

Max Act: 3.4244. Min Act: -0.1700

Data Index: 8157524 (Open Web Text)

Max Activating Token Index: 623