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

Dataset: Open Web Text

Neuron 1855 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: 5.3290. Min Range: -5.3290

Max Act: 5.3204. Min Act: -0.1700

Data Index: 8807545 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.3290. Min Act: -0.1700

Data Index: 7244921 (Open Web Text)

Max Activating Token Index: 970

Text #2

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2972. Min Act: -0.1700

Data Index: 6017263 (Open Web Text)

Max Activating Token Index: 957

Text #3

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2406. Min Act: -0.1700

Data Index: 5305866 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2480. Min Act: -0.1700

Data Index: 4451815 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2206. Min Act: -0.1700

Data Index: 407317 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2280. Min Act: -0.1700

Data Index: 4863008 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2263. Min Act: -0.1700

Data Index: 6544856 (Open Web Text)

Max Activating Token Index: 784

Text #8

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2521. Min Act: -0.1700

Data Index: 6785748 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.2335. Min Act: -0.1700

Data Index: 6792127 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1948. Min Act: -0.1700

Data Index: 8557727 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1999. Min Act: -0.1700

Data Index: 2861077 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1590. Min Act: -0.1700

Data Index: 7518931 (Open Web Text)

Max Activating Token Index: 666

Text #13

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1721. Min Act: -0.1700

Data Index: 546295 (Open Web Text)

Max Activating Token Index: 684

Text #14

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1825. Min Act: -0.1700

Data Index: 935857 (Open Web Text)

Max Activating Token Index: 235

Text #15

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1817. Min Act: -0.1700

Data Index: 6158493 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1545. Min Act: -0.1700

Data Index: 2669126 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1857. Min Act: -0.1700

Data Index: 4303413 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1552. Min Act: -0.1700

Data Index: 5882422 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 5.3290. Min Range: -5.3290

Max Act: 5.1379. Min Act: -0.1700

Data Index: 3823046 (Open Web Text)

Max Activating Token Index: 940