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

Dataset: Open Web Text

Neuron 1134 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: 3.8150. Min Range: -3.8150

Max Act: 3.8150. Min Act: -0.1700

Data Index: 280538 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7399. Min Act: -0.1700

Data Index: 624399 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7543. Min Act: -0.1700

Data Index: 1734217 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7275. Min Act: -0.1700

Data Index: 7967824 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6941. Min Act: -0.1700

Data Index: 2197720 (Open Web Text)

Max Activating Token Index: 616

Text #5

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6979. Min Act: -0.1700

Data Index: 1415279 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7133. Min Act: -0.1700

Data Index: 3809398 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6902. Min Act: -0.1700

Data Index: 7148591 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7118. Min Act: -0.1700

Data Index: 3347317 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7201. Min Act: -0.1700

Data Index: 7072925 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6902. Min Act: -0.1700

Data Index: 3117410 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6803. Min Act: -0.1700

Data Index: 5696471 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6988. Min Act: -0.1700

Data Index: 303762 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6708. Min Act: -0.1700

Data Index: 4917919 (Open Web Text)

Max Activating Token Index: 46

Text #14

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6867. Min Act: -0.1700

Data Index: 4642063 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6837. Min Act: -0.1700

Data Index: 3850045 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6978. Min Act: -0.1700

Data Index: 1539888 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6989. Min Act: -0.1700

Data Index: 4250526 (Open Web Text)

Max Activating Token Index: 926

Text #18

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.7036. Min Act: -0.1700

Data Index: 2562131 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 3.8150. Min Range: -3.8150

Max Act: 3.6900. Min Act: -0.1700

Data Index: 8159443 (Open Web Text)

Max Activating Token Index: 458