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

Dataset: Open Web Text

Neuron 98 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: 3.3921. Min Range: -3.3921

Max Act: 3.3853. Min Act: -0.1700

Data Index: 4965025 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.3921. Min Act: -0.1700

Data Index: 6989904 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2919. Min Act: -0.1700

Data Index: 8466901 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1294132 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2726. Min Act: -0.1700

Data Index: 831585 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2693. Min Act: -0.1700

Data Index: 5795065 (Open Web Text)

Max Activating Token Index: 392

Text #6

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2892. Min Act: -0.1700

Data Index: 4089586 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2630. Min Act: -0.1700

Data Index: 2207972 (Open Web Text)

Max Activating Token Index: 578

Text #8

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2760. Min Act: -0.1700

Data Index: 5461653 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2654. Min Act: -0.1700

Data Index: 7561195 (Open Web Text)

Max Activating Token Index: 999

Text #10

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2574. Min Act: -0.1700

Data Index: 1808100 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2619. Min Act: -0.1700

Data Index: 6004057 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2504. Min Act: -0.1700

Data Index: 518105 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2593. Min Act: -0.1700

Data Index: 518104 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2414. Min Act: -0.1700

Data Index: 676294 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2425. Min Act: -0.1700

Data Index: 3181866 (Open Web Text)

Max Activating Token Index: 875

Text #16

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1136305 (Open Web Text)

Max Activating Token Index: 51

Text #17

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1344495 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2585. Min Act: -0.1700

Data Index: 2256493 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2362. Min Act: -0.1700

Data Index: 3553180 (Open Web Text)

Max Activating Token Index: 263