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

Dataset: Open Web Text

Neuron 2061 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: 5.9090. Min Range: -5.9090

Max Act: 5.9090. Min Act: -0.1700

Data Index: 819246 (Open Web Text)

Max Activating Token Index: 131

Text #1

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.5658. Min Act: -0.1700

Data Index: 8823162 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.5402. Min Act: -0.1700

Data Index: 2159087 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.5679. Min Act: -0.1700

Data Index: 1335080 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4571. Min Act: -0.1700

Data Index: 3688513 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4359. Min Act: -0.1700

Data Index: 7405603 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4411. Min Act: -0.1700

Data Index: 7291379 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4390. Min Act: -0.1700

Data Index: 5799758 (Open Web Text)

Max Activating Token Index: 75

Text #8

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4013. Min Act: -0.1700

Data Index: 6602785 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.4103. Min Act: -0.1700

Data Index: 6320414 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3982. Min Act: -0.1700

Data Index: 2552640 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3673. Min Act: -0.1700

Data Index: 1758371 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3543. Min Act: -0.1700

Data Index: 6813917 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3349. Min Act: -0.1700

Data Index: 5898427 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3179. Min Act: -0.1700

Data Index: 61688 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3450. Min Act: -0.1700

Data Index: 7768210 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3398. Min Act: -0.1700

Data Index: 4385126 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3276. Min Act: -0.1700

Data Index: 8428844 (Open Web Text)

Max Activating Token Index: 743

Text #18

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3238. Min Act: -0.1700

Data Index: 270616 (Open Web Text)

Max Activating Token Index: 855

Text #19

Max Range: 5.9090. Min Range: -5.9090

Max Act: 5.3453. Min Act: -0.1700

Data Index: 7546815 (Open Web Text)

Max Activating Token Index: 566