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

Dataset: Open Web Text

Neuron 1655 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: 3.7414. Min Range: -3.7414

Max Act: 3.7414. Min Act: -0.1700

Data Index: 2845294 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.7077. Min Act: -0.1700

Data Index: 4379223 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.7209. Min Act: -0.1700

Data Index: 6865949 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.7281. Min Act: -0.1700

Data Index: 3992862 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.7065. Min Act: -0.1700

Data Index: 2776650 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6860. Min Act: -0.1700

Data Index: 7199139 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6924. Min Act: -0.1700

Data Index: 3546047 (Open Web Text)

Max Activating Token Index: 839

Text #7

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6828. Min Act: -0.1700

Data Index: 70774 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6613. Min Act: -0.1700

Data Index: 6967969 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6569. Min Act: -0.1700

Data Index: 6794854 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6505. Min Act: -0.1700

Data Index: 4081058 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6448. Min Act: -0.1700

Data Index: 608236 (Open Web Text)

Max Activating Token Index: 635

Text #12

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6452. Min Act: -0.1700

Data Index: 79568 (Open Web Text)

Max Activating Token Index: 844

Text #13

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6518. Min Act: -0.1700

Data Index: 5051775 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6231. Min Act: -0.1700

Data Index: 5840501 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6345. Min Act: -0.1700

Data Index: 5707359 (Open Web Text)

Max Activating Token Index: 243

Text #16

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1330559 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1141345 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1606040 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 3.7414. Min Range: -3.7414

Max Act: 3.6124. Min Act: -0.1700

Data Index: 3360615 (Open Web Text)

Max Activating Token Index: 555