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

Dataset: Open Web Text

Neuron 1831 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: 0.7166. Min Range: -0.7166

Max Act: 0.7166. Min Act: -0.1700

Data Index: 7422578 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.7147. Min Act: -0.1700

Data Index: 1813271 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6960. Min Act: -0.1700

Data Index: 501967 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6886. Min Act: -0.1700

Data Index: 6947224 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6883. Min Act: -0.1700

Data Index: 1220335 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6958. Min Act: -0.1700

Data Index: 8312995 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6963. Min Act: -0.1700

Data Index: 5761536 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6891. Min Act: -0.1700

Data Index: 641520 (Open Web Text)

Max Activating Token Index: 331

Text #8

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6868. Min Act: -0.1700

Data Index: 1764215 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6874. Min Act: -0.1700

Data Index: 99821 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6831. Min Act: -0.1700

Data Index: 1796656 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6842. Min Act: -0.1700

Data Index: 6002617 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6866. Min Act: -0.1700

Data Index: 6757687 (Open Web Text)

Max Activating Token Index: 333

Text #13

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6841. Min Act: -0.1700

Data Index: 7174697 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6862. Min Act: -0.1700

Data Index: 4651840 (Open Web Text)

Max Activating Token Index: 348

Text #15

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6736. Min Act: -0.1700

Data Index: 433842 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6752. Min Act: -0.1700

Data Index: 1969544 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6804. Min Act: -0.1700

Data Index: 3620244 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6826. Min Act: -0.1700

Data Index: 3622981 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 0.7166. Min Range: -0.7166

Max Act: 0.6771. Min Act: -0.1700

Data Index: 3858180 (Open Web Text)

Max Activating Token Index: 327