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

Dataset: Open Web Text

Neuron 1264 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: 3.0070. Min Range: -3.0070

Max Act: 3.0070. Min Act: -0.1700

Data Index: 4353437 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.9531. Min Act: -0.1700

Data Index: 4626447 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.9639. Min Act: -0.1700

Data Index: 8624883 (Open Web Text)

Max Activating Token Index: 84

Text #3

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.9050. Min Act: -0.1700

Data Index: 3194095 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8946. Min Act: -0.1700

Data Index: 521164 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8802. Min Act: -0.1700

Data Index: 5607921 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8964. Min Act: -0.1700

Data Index: 4087252 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8894. Min Act: -0.1700

Data Index: 3194093 (Open Web Text)

Max Activating Token Index: 245

Text #8

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8713. Min Act: -0.1700

Data Index: 3664202 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8785. Min Act: -0.1700

Data Index: 3194094 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8717. Min Act: -0.1700

Data Index: 2179191 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8673. Min Act: -0.1700

Data Index: 3194092 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8504. Min Act: -0.1700

Data Index: 1129985 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8714. Min Act: -0.1700

Data Index: 3884583 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8579. Min Act: -0.1700

Data Index: 857587 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8562. Min Act: -0.1700

Data Index: 6070538 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8466. Min Act: -0.1700

Data Index: 4155188 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8405. Min Act: -0.1700

Data Index: 1690947 (Open Web Text)

Max Activating Token Index: 980

Text #18

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8614. Min Act: -0.1700

Data Index: 4436492 (Open Web Text)

Max Activating Token Index: 936

Text #19

Max Range: 3.0070. Min Range: -3.0070

Max Act: 2.8417. Min Act: -0.1700

Data Index: 3251467 (Open Web Text)

Max Activating Token Index: 236