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

Dataset: Open Web Text

Neuron 411 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: 1.8104. Min Range: -1.8104

Max Act: 1.8104. Min Act: -0.1700

Data Index: 1069468 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7874. Min Act: -0.1700

Data Index: 6205239 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7740. Min Act: -0.1698

Data Index: 7569772 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7749. Min Act: -0.1700

Data Index: 4465525 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7455. Min Act: -0.1700

Data Index: 6448219 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7369. Min Act: -0.1700

Data Index: 4418178 (Open Web Text)

Max Activating Token Index: 235

Text #6

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7384. Min Act: -0.1700

Data Index: 6900679 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7361. Min Act: -0.1700

Data Index: 4252071 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7233. Min Act: -0.1698

Data Index: 5071027 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7193. Min Act: -0.1699

Data Index: 4332862 (Open Web Text)

Max Activating Token Index: 104

Text #10

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7074. Min Act: -0.1699

Data Index: 4632078 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7094. Min Act: -0.1700

Data Index: 1885767 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7090. Min Act: -0.1700

Data Index: 2055247 (Open Web Text)

Max Activating Token Index: 261

Text #13

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7002. Min Act: -0.1699

Data Index: 3021730 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6988. Min Act: -0.1700

Data Index: 3848298 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6884. Min Act: -0.1700

Data Index: 1453013 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6939. Min Act: -0.1700

Data Index: 7189414 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6939. Min Act: -0.1700

Data Index: 5209171 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.7009. Min Act: -0.1700

Data Index: 8299024 (Open Web Text)

Max Activating Token Index: 288

Text #19

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6998. Min Act: -0.1700

Data Index: 7507052 (Open Web Text)

Max Activating Token Index: 260