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

Dataset: Open Web Text

Neuron 1664 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: 3.6013. Min Range: -3.6013

Max Act: 3.6013. Min Act: -0.1700

Data Index: 5187779 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5397. Min Act: -0.1700

Data Index: 6573669 (Open Web Text)

Max Activating Token Index: 845

Text #2

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4793. Min Act: -0.1700

Data Index: 2392682 (Open Web Text)

Max Activating Token Index: 193

Text #3

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5666. Min Act: -0.1700

Data Index: 3121263 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4976. Min Act: -0.1700

Data Index: 6920522 (Open Web Text)

Max Activating Token Index: 862

Text #5

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5461. Min Act: -0.1700

Data Index: 3656439 (Open Web Text)

Max Activating Token Index: 683

Text #6

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4601. Min Act: -0.1700

Data Index: 3511467 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5079. Min Act: -0.1700

Data Index: 8602335 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5130. Min Act: -0.1697

Data Index: 8234069 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.5171. Min Act: -0.1700

Data Index: 2577276 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4504. Min Act: -0.1700

Data Index: 3990642 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4491. Min Act: -0.1700

Data Index: 5543723 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4752. Min Act: -0.1700

Data Index: 4083617 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4452. Min Act: -0.1700

Data Index: 3440529 (Open Web Text)

Max Activating Token Index: 609

Text #14

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1353544 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4446. Min Act: -0.1700

Data Index: 2336865 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.3964. Min Act: -0.1700

Data Index: 2363681 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4223. Min Act: -0.1700

Data Index: 1320615 (Open Web Text)

Max Activating Token Index: 494

Text #18

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4244. Min Act: -0.1700

Data Index: 3527416 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 3.6013. Min Range: -3.6013

Max Act: 3.4598. Min Act: -0.1700

Data Index: 3720489 (Open Web Text)

Max Activating Token Index: 856