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

Dataset: Open Web Text

Neuron 570 in Layer 4

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: 3.7746. Min Range: -3.7746

Max Act: 3.7746. Min Act: -0.1700

Data Index: 4352367 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.7285. Min Act: -0.1700

Data Index: 4872029 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.7029. Min Act: -0.1700

Data Index: 472281 (Open Web Text)

Max Activating Token Index: 76

Text #3

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6771. Min Act: -0.1700

Data Index: 7935537 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.7085. Min Act: -0.1700

Data Index: 4909112 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.7060. Min Act: -0.1700

Data Index: 6315237 (Open Web Text)

Max Activating Token Index: 851

Text #6

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6844. Min Act: -0.1700

Data Index: 918776 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6561. Min Act: -0.1700

Data Index: 1442944 (Open Web Text)

Max Activating Token Index: 613

Text #8

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6265. Min Act: -0.1700

Data Index: 692339 (Open Web Text)

Max Activating Token Index: 893

Text #9

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6431. Min Act: -0.1700

Data Index: 2242674 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1627151 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6335. Min Act: -0.1700

Data Index: 8466206 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6327. Min Act: -0.1700

Data Index: 1496460 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6353. Min Act: -0.1700

Data Index: 2500280 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6069. Min Act: -0.1700

Data Index: 7898102 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6056. Min Act: -0.1700

Data Index: 48921 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6314. Min Act: -0.1700

Data Index: 3456943 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6107. Min Act: -0.1700

Data Index: 767310 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6094. Min Act: -0.1700

Data Index: 6235052 (Open Web Text)

Max Activating Token Index: 423

Text #19

Max Range: 3.7746. Min Range: -3.7746

Max Act: 3.6246. Min Act: -0.1700

Data Index: 1599467 (Open Web Text)

Max Activating Token Index: 613