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

Dataset: Open Web Text

Neuron 2681 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: 1.6976. Min Range: -1.6976

Max Act: 1.6976. Min Act: -0.1700

Data Index: 4858796 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6777. Min Act: -0.1700

Data Index: 5356440 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6608. Min Act: -0.1700

Data Index: 7499178 (Open Web Text)

Max Activating Token Index: 380

Text #3

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6604. Min Act: -0.1700

Data Index: 1747301 (Open Web Text)

Max Activating Token Index: 578

Text #4

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6464. Min Act: -0.1700

Data Index: 1757026 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6428. Min Act: -0.1699

Data Index: 7772387 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6449. Min Act: -0.1700

Data Index: 5712200 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6398. Min Act: -0.1700

Data Index: 8496006 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6404. Min Act: -0.1700

Data Index: 6042299 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6302. Min Act: -0.1700

Data Index: 7086774 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6305. Min Act: -0.1700

Data Index: 6435113 (Open Web Text)

Max Activating Token Index: 555

Text #11

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6107. Min Act: -0.1700

Data Index: 7454834 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6144. Min Act: -0.1699

Data Index: 2382110 (Open Web Text)

Max Activating Token Index: 76

Text #13

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6062. Min Act: -0.1700

Data Index: 6107883 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6074. Min Act: -0.1700

Data Index: 2196454 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6075. Min Act: -0.1699

Data Index: 1111269 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5986. Min Act: -0.1700

Data Index: 6058869 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5994. Min Act: -0.1700

Data Index: 2263525 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5997. Min Act: -0.1700

Data Index: 4476086 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5884. Min Act: -0.1700

Data Index: 5594836 (Open Web Text)

Max Activating Token Index: 224