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

Dataset: Open Web Text

Neuron 1169 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: 4.9254. Min Range: -4.9254

Max Act: 4.8948. Min Act: -0.1700

Data Index: 5911238 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.9254. Min Act: -0.1700

Data Index: 3979158 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.9235. Min Act: -0.1700

Data Index: 1124463 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.9185. Min Act: -0.1700

Data Index: 6296703 (Open Web Text)

Max Activating Token Index: 204

Text #4

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8745. Min Act: -0.1700

Data Index: 3889246 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8776. Min Act: -0.1700

Data Index: 2140581 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8855. Min Act: -0.1700

Data Index: 8304028 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8813. Min Act: -0.1700

Data Index: 2817879 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8560. Min Act: -0.1700

Data Index: 780152 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8358. Min Act: -0.1700

Data Index: 7391622 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8491. Min Act: -0.1700

Data Index: 7894081 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8538. Min Act: -0.1700

Data Index: 1829121 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8113. Min Act: -0.1700

Data Index: 5947515 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8161. Min Act: -0.1700

Data Index: 1830305 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8011. Min Act: -0.1700

Data Index: 7257683 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8097. Min Act: -0.1700

Data Index: 7316633 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8290. Min Act: -0.1700

Data Index: 4224277 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8322. Min Act: -0.1700

Data Index: 7628435 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8105. Min Act: -0.1700

Data Index: 2341883 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 4.9254. Min Range: -4.9254

Max Act: 4.8045. Min Act: -0.1700

Data Index: 4663881 (Open Web Text)

Max Activating Token Index: 234