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

Dataset: Open Web Text

Neuron 2667 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: 3.6129. Min Range: -3.6129

Max Act: 3.6052. Min Act: -0.1700

Data Index: 5003049 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.6061. Min Act: -0.1700

Data Index: 2061759 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.6067. Min Act: -0.1700

Data Index: 8389908 (Open Web Text)

Max Activating Token Index: 347

Text #3

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.6129. Min Act: -0.1700

Data Index: 4504450 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5789. Min Act: -0.1700

Data Index: 5627348 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5375. Min Act: -0.1700

Data Index: 4971886 (Open Web Text)

Max Activating Token Index: 73

Text #6

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5363. Min Act: -0.1700

Data Index: 8762740 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5283. Min Act: -0.1700

Data Index: 8569371 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5505. Min Act: -0.1700

Data Index: 5070010 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5549. Min Act: -0.1700

Data Index: 959705 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5509. Min Act: -0.1700

Data Index: 5313129 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5411. Min Act: -0.1700

Data Index: 6484330 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5480. Min Act: -0.1700

Data Index: 7440083 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.4913. Min Act: -0.1700

Data Index: 2700520 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5280. Min Act: -0.1700

Data Index: 2526909 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5460. Min Act: -0.1700

Data Index: 3113473 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5038. Min Act: -0.1700

Data Index: 4236115 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5179. Min Act: -0.1700

Data Index: 2793363 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5383. Min Act: -0.1700

Data Index: 3904653 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.5019. Min Act: -0.1700

Data Index: 2302877 (Open Web Text)

Max Activating Token Index: 545