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

Dataset: Open Web Text

Neuron 2665 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: 3.9356. Min Range: -3.9356

Max Act: 3.9356. Min Act: -0.1700

Data Index: 1448902 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6794. Min Act: -0.1700

Data Index: 1402008 (Open Web Text)

Max Activating Token Index: 233

Text #2

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.7392. Min Act: -0.1700

Data Index: 6239111 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6674. Min Act: -0.1700

Data Index: 2302855 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6612. Min Act: -0.1700

Data Index: 4974286 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6657. Min Act: -0.1700

Data Index: 4761421 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6549. Min Act: -0.1700

Data Index: 5136529 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6364. Min Act: -0.1700

Data Index: 404224 (Open Web Text)

Max Activating Token Index: 162

Text #8

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6136. Min Act: -0.1700

Data Index: 7334113 (Open Web Text)

Max Activating Token Index: 864

Text #9

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6294. Min Act: -0.1700

Data Index: 881418 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6183. Min Act: -0.1700

Data Index: 5402473 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6173. Min Act: -0.1700

Data Index: 8267740 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.5632. Min Act: -0.1700

Data Index: 6155400 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6018. Min Act: -0.1700

Data Index: 4123403 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.5947. Min Act: -0.1700

Data Index: 3989813 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1453119 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.6081. Min Act: -0.1700

Data Index: 6954838 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.5904. Min Act: -0.1700

Data Index: 2297518 (Open Web Text)

Max Activating Token Index: 346

Text #18

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.5999. Min Act: -0.1700

Data Index: 2265908 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 3.9356. Min Range: -3.9356

Max Act: 3.5665. Min Act: -0.1700

Data Index: 188042 (Open Web Text)

Max Activating Token Index: 230