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

Dataset: Open Web Text

Neuron 1114 in Layer 6

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: 4.0474. Min Range: -4.0474

Max Act: 4.0474. Min Act: -0.1700

Data Index: 2128359 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9970. Min Act: -0.1700

Data Index: 1352378 (Open Web Text)

Max Activating Token Index: 107

Text #2

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9475. Min Act: -0.1700

Data Index: 3613472 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9286. Min Act: -0.1700

Data Index: 2232942 (Open Web Text)

Max Activating Token Index: 398

Text #4

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9438. Min Act: -0.1700

Data Index: 2478507 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8844. Min Act: -0.1700

Data Index: 4041799 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.9015. Min Act: -0.1700

Data Index: 5574563 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8308. Min Act: -0.1700

Data Index: 320274 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8596. Min Act: -0.1700

Data Index: 7987628 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8562. Min Act: -0.1700

Data Index: 5836506 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8504. Min Act: -0.1700

Data Index: 2134883 (Open Web Text)

Max Activating Token Index: 712

Text #11

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8150. Min Act: -0.1700

Data Index: 7494523 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8461. Min Act: -0.1700

Data Index: 3560633 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8348. Min Act: -0.1700

Data Index: 5257099 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8430. Min Act: -0.1700

Data Index: 2383255 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8379. Min Act: -0.1700

Data Index: 1254981 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8370. Min Act: -0.1700

Data Index: 7127091 (Open Web Text)

Max Activating Token Index: 734

Text #17

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8301. Min Act: -0.1700

Data Index: 1209335 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8199. Min Act: -0.1700

Data Index: 922892 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 4.0474. Min Range: -4.0474

Max Act: 3.8121. Min Act: -0.1700

Data Index: 5958731 (Open Web Text)

Max Activating Token Index: 956