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

Dataset: Open Web Text

Neuron 102 in Layer 4

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: 3.1822. Min Range: -3.1822

Max Act: 3.1822. Min Act: -0.1700

Data Index: 3092857 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0540. Min Act: -0.1700

Data Index: 3721723 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0327. Min Act: -0.1700

Data Index: 5093474 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9915. Min Act: -0.1700

Data Index: 3999870 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0060. Min Act: -0.1700

Data Index: 2869933 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9972. Min Act: -0.1700

Data Index: 1712066 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9913. Min Act: -0.1700

Data Index: 35687 (Open Web Text)

Max Activating Token Index: 609

Text #7

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9873. Min Act: -0.1700

Data Index: 6598790 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1213128 (Open Web Text)

Max Activating Token Index: 619

Text #9

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9571. Min Act: -0.1700

Data Index: 8053413 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9547. Min Act: -0.1700

Data Index: 7180582 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9363. Min Act: -0.1700

Data Index: 5765862 (Open Web Text)

Max Activating Token Index: 455

Text #12

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9405. Min Act: -0.1700

Data Index: 1309365 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9285. Min Act: -0.1700

Data Index: 5724404 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.8948. Min Act: -0.1700

Data Index: 6294159 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9496. Min Act: -0.1700

Data Index: 680987 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.9238. Min Act: -0.1700

Data Index: 3617790 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.8539. Min Act: -0.1700

Data Index: 5010664 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.8998. Min Act: -0.1700

Data Index: 3439792 (Open Web Text)

Max Activating Token Index: 65

Text #19

Max Range: 3.1822. Min Range: -3.1822

Max Act: 2.8696. Min Act: -0.1700

Data Index: 3777441 (Open Web Text)

Max Activating Token Index: 493