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

Dataset: Open Web Text

Neuron 3007 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: 4.4238. Min Range: -4.4238

Max Act: 4.4238. Min Act: -0.1700

Data Index: 8740982 (Open Web Text)

Max Activating Token Index: 652

Text #1

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.3960. Min Act: -0.1700

Data Index: 3029202 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.3755. Min Act: -0.1700

Data Index: 4477434 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.3181. Min Act: -0.1700

Data Index: 5781202 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.3427. Min Act: -0.1700

Data Index: 8103636 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2873. Min Act: -0.1700

Data Index: 1466920 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2575. Min Act: -0.1700

Data Index: 6973363 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2924. Min Act: -0.1700

Data Index: 8582597 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2263. Min Act: -0.1700

Data Index: 4240745 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2105. Min Act: -0.1700

Data Index: 269427 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2522. Min Act: -0.1700

Data Index: 4068862 (Open Web Text)

Max Activating Token Index: 713

Text #11

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2717. Min Act: -0.1700

Data Index: 3891399 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.1905. Min Act: -0.1700

Data Index: 5090447 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2357. Min Act: -0.1700

Data Index: 622035 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2341. Min Act: -0.1700

Data Index: 1555357 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.1963. Min Act: -0.1700

Data Index: 1569672 (Open Web Text)

Max Activating Token Index: 983

Text #16

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2337. Min Act: -0.1700

Data Index: 4756863 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2594. Min Act: -0.1700

Data Index: 1579313 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2629. Min Act: -0.1700

Data Index: 4971072 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 4.4238. Min Range: -4.4238

Max Act: 4.2353. Min Act: -0.1700

Data Index: 3564261 (Open Web Text)

Max Activating Token Index: 981