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

Dataset: Open Web Text

Neuron 64 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: 3.4479. Min Range: -3.4479

Max Act: 3.4479. Min Act: -0.1700

Data Index: 7379504 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.2358. Min Act: -0.1700

Data Index: 8490266 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.2829. Min Act: -0.1700

Data Index: 4344911 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.2489. Min Act: -0.1700

Data Index: 6030311 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1889. Min Act: -0.1700

Data Index: 8017278 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1919. Min Act: -0.1700

Data Index: 6541556 (Open Web Text)

Max Activating Token Index: 153

Text #6

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1712. Min Act: -0.1700

Data Index: 3671986 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1129. Min Act: -0.1700

Data Index: 729068 (Open Web Text)

Max Activating Token Index: 114

Text #8

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1273. Min Act: -0.1700

Data Index: 1375168 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0920. Min Act: -0.1700

Data Index: 5824886 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0903. Min Act: -0.1700

Data Index: 5069708 (Open Web Text)

Max Activating Token Index: 626

Text #11

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1202062 (Open Web Text)

Max Activating Token Index: 698

Text #12

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0755. Min Act: -0.1700

Data Index: 8788744 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0991. Min Act: -0.1700

Data Index: 2818933 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1116. Min Act: -0.1700

Data Index: 5237090 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1001. Min Act: -0.1700

Data Index: 8745185 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.1095. Min Act: -0.1700

Data Index: 7227778 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0664. Min Act: -0.1700

Data Index: 5725229 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0730. Min Act: -0.1700

Data Index: 7155228 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 3.4479. Min Range: -3.4479

Max Act: 3.0579. Min Act: -0.1700

Data Index: 4560791 (Open Web Text)

Max Activating Token Index: 610