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

Dataset: Open Web Text

Neuron 110 in Layer 3

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: 3.8251. Min Range: -3.8251

Max Act: 3.8251. Min Act: -0.1700

Data Index: 2978535 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.8028. Min Act: -0.1700

Data Index: 4457728 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.7760. Min Act: -0.1700

Data Index: 7389138 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.7653. Min Act: -0.1700

Data Index: 312067 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.7470. Min Act: -0.1700

Data Index: 2827930 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.7697. Min Act: -0.1700

Data Index: 3890317 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.7268. Min Act: -0.1700

Data Index: 1674029 (Open Web Text)

Max Activating Token Index: 366

Text #7

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6677. Min Act: -0.1700

Data Index: 7389137 (Open Web Text)

Max Activating Token Index: 368

Text #8

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6799. Min Act: -0.1700

Data Index: 8141431 (Open Web Text)

Max Activating Token Index: 113

Text #9

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6735. Min Act: -0.1700

Data Index: 2936150 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6676. Min Act: -0.1700

Data Index: 3873210 (Open Web Text)

Max Activating Token Index: 968

Text #11

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6662. Min Act: -0.1700

Data Index: 2936145 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6558. Min Act: -0.1700

Data Index: 4798428 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6129. Min Act: -0.1700

Data Index: 7531986 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.5916. Min Act: -0.1700

Data Index: 3118775 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6211. Min Act: -0.1700

Data Index: 8750045 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.6049. Min Act: -0.1700

Data Index: 5700084 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.5689. Min Act: -0.1700

Data Index: 4499235 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.5727. Min Act: -0.1700

Data Index: 8095784 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 3.8251. Min Range: -3.8251

Max Act: 3.5990. Min Act: -0.1700

Data Index: 1765639 (Open Web Text)

Max Activating Token Index: 180