Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3029 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.9064. Min Act: -0.1700

Data Index: 8436565 (Open Web Text)

Max Activating Token Index: 752

Text #1

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.9064. Min Act: -0.1700

Data Index: 8508107 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.4064. Min Act: -0.1700

Data Index: 5041801 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.4064. Min Act: -0.1700

Data Index: 6218627 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3751. Min Act: -0.1700

Data Index: 5410307 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3439. Min Act: -0.1700

Data Index: 4013118 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3439. Min Act: -0.1700

Data Index: 4525750 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3126. Min Act: -0.1700

Data Index: 6318219 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.3126. Min Act: -0.1700

Data Index: 4809447 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2814. Min Act: -0.1700

Data Index: 2586944 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2814. Min Act: -0.1700

Data Index: 516894 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2814. Min Act: -0.1700

Data Index: 5252530 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2814. Min Act: -0.1700

Data Index: 280057 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2501. Min Act: -0.1700

Data Index: 6971552 (Open Web Text)

Max Activating Token Index: 370

Text #14

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2189. Min Act: -0.1700

Data Index: 6811289 (Open Web Text)

Max Activating Token Index: 927

Text #15

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2189. Min Act: -0.1700

Data Index: 8218545 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.2189. Min Act: -0.1700

Data Index: 2625514 (Open Web Text)

Max Activating Token Index: 253

Text #17

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1876. Min Act: -0.1700

Data Index: 4379072 (Open Web Text)

Max Activating Token Index: 896

Text #18

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1564. Min Act: -0.1700

Data Index: 6110595 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 7.9064. Min Range: -7.9064

Max Act: 7.1564. Min Act: -0.1700

Data Index: 6096959 (Open Web Text)

Max Activating Token Index: 647