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

Dataset: Open Web Text

Neuron 189 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: 3.5951. Min Range: -3.5951

Max Act: 3.5951. Min Act: -0.1700

Data Index: 2818367 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.5740. Min Act: -0.1700

Data Index: 7903736 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.5154. Min Act: -0.1700

Data Index: 1237354 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.5127. Min Act: -0.1700

Data Index: 8181568 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.4698. Min Act: -0.1700

Data Index: 6798556 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.4709. Min Act: -0.1700

Data Index: 7920352 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.4337. Min Act: -0.1700

Data Index: 7805842 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.4312. Min Act: -0.1700

Data Index: 4136512 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.4135. Min Act: -0.1700

Data Index: 2545744 (Open Web Text)

Max Activating Token Index: 617

Text #9

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3934. Min Act: -0.1700

Data Index: 8754500 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3742. Min Act: -0.1700

Data Index: 6324213 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3656. Min Act: -0.1700

Data Index: 5513234 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3665. Min Act: -0.1700

Data Index: 7979222 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3235. Min Act: -0.1700

Data Index: 138705 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3680. Min Act: -0.1700

Data Index: 8607379 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3615. Min Act: -0.1700

Data Index: 4675758 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3408. Min Act: -0.1700

Data Index: 2602368 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3419. Min Act: -0.1700

Data Index: 5394546 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1552232 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 3.5951. Min Range: -3.5951

Max Act: 3.3367. Min Act: -0.1700

Data Index: 2246728 (Open Web Text)

Max Activating Token Index: 865