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

Dataset: Open Web Text

Neuron 1384 in Layer 5

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: 4.3251. Min Range: -4.3251

Max Act: 4.3251. Min Act: -0.1700

Data Index: 7310645 (Open Web Text)

Max Activating Token Index: 437

Text #1

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.2496. Min Act: -0.1700

Data Index: 3832716 (Open Web Text)

Max Activating Token Index: 770

Text #2

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.2655. Min Act: -0.1700

Data Index: 723880 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.1201. Min Act: -0.1700

Data Index: 3027540 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.1063. Min Act: -0.1700

Data Index: 2171340 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.1419. Min Act: -0.1700

Data Index: 3040913 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.1013. Min Act: -0.1700

Data Index: 2196249 (Open Web Text)

Max Activating Token Index: 555

Text #7

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0546. Min Act: -0.1700

Data Index: 2529105 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0452. Min Act: -0.1700

Data Index: 4589791 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0361. Min Act: -0.1700

Data Index: 7477421 (Open Web Text)

Max Activating Token Index: 414

Text #10

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0525. Min Act: -0.1700

Data Index: 1301291 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0550. Min Act: -0.1700

Data Index: 7441179 (Open Web Text)

Max Activating Token Index: 314

Text #12

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0197. Min Act: -0.1700

Data Index: 5248702 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0491. Min Act: -0.1700

Data Index: 5450036 (Open Web Text)

Max Activating Token Index: 129

Text #14

Max Range: 4.3251. Min Range: -4.3251

Max Act: 3.9866. Min Act: -0.1700

Data Index: 3069785 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0102. Min Act: -0.1700

Data Index: 6231224 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 4.3251. Min Range: -4.3251

Max Act: 4.0425. Min Act: -0.1700

Data Index: 4341820 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 4.3251. Min Range: -4.3251

Max Act: 3.9771. Min Act: -0.1700

Data Index: 4503751 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 4.3251. Min Range: -4.3251

Max Act: 3.9776. Min Act: -0.1700

Data Index: 6243220 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 4.3251. Min Range: -4.3251

Max Act: 3.9565. Min Act: -0.1700

Data Index: 6384492 (Open Web Text)

Max Activating Token Index: 776