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

Dataset: Open Web Text

Neuron 2656 in Layer 1

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: 1.5918. Min Range: -1.5918

Max Act: 1.5918. Min Act: -0.1700

Data Index: 2207398 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5494. Min Act: -0.1700

Data Index: 559443 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5435. Min Act: -0.1700

Data Index: 7787184 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5418. Min Act: -0.1700

Data Index: 5971609 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5247. Min Act: -0.1700

Data Index: 1749697 (Open Web Text)

Max Activating Token Index: 177

Text #5

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5283. Min Act: -0.1700

Data Index: 8061027 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5062. Min Act: -0.1700

Data Index: 2327872 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5186. Min Act: -0.1700

Data Index: 5364396 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5060. Min Act: -0.1700

Data Index: 5331240 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5052. Min Act: -0.1700

Data Index: 2920877 (Open Web Text)

Max Activating Token Index: 960

Text #10

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4918. Min Act: -0.1700

Data Index: 7105074 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4931. Min Act: -0.1700

Data Index: 2765672 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4950. Min Act: -0.1700

Data Index: 3880324 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4976. Min Act: -0.1700

Data Index: 2866956 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4948. Min Act: -0.1700

Data Index: 8677533 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4842. Min Act: -0.1700

Data Index: 6131206 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4824. Min Act: -0.1700

Data Index: 4591255 (Open Web Text)

Max Activating Token Index: 374

Text #17

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4875. Min Act: -0.1700

Data Index: 5374170 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4907. Min Act: -0.1700

Data Index: 2625622 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4803. Min Act: -0.1700

Data Index: 6258376 (Open Web Text)

Max Activating Token Index: 661