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

Dataset: Open Web Text

Neuron 344 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: 3.4340. Min Range: -3.4340

Max Act: 3.4340. Min Act: -0.1700

Data Index: 6817750 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.3666. Min Act: -0.1700

Data Index: 8189034 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.3550. Min Act: -0.1700

Data Index: 5781301 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.3063. Min Act: -0.1700

Data Index: 4000470 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.3049. Min Act: -0.1700

Data Index: 5384503 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1420496 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2987. Min Act: -0.1700

Data Index: 6007485 (Open Web Text)

Max Activating Token Index: 165

Text #7

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2743. Min Act: -0.1700

Data Index: 8290686 (Open Web Text)

Max Activating Token Index: 670

Text #8

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2969. Min Act: -0.1700

Data Index: 4380977 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2901. Min Act: -0.1700

Data Index: 5618415 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2923. Min Act: -0.1700

Data Index: 3492598 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2934. Min Act: -0.1700

Data Index: 807442 (Open Web Text)

Max Activating Token Index: 871

Text #12

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2686. Min Act: -0.1700

Data Index: 4486733 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2668. Min Act: -0.1700

Data Index: 2168111 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2156. Min Act: -0.1700

Data Index: 8067255 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2362. Min Act: -0.1700

Data Index: 754753 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2402. Min Act: -0.1700

Data Index: 392631 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2149. Min Act: -0.1700

Data Index: 5313489 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2192. Min Act: -0.1700

Data Index: 3910805 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 3.4340. Min Range: -3.4340

Max Act: 3.2103. Min Act: -0.1700

Data Index: 7102732 (Open Web Text)

Max Activating Token Index: 449