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

Dataset: Open Web Text

Neuron 1317 in Layer 1

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: 0.8997. Min Range: -0.8997

Max Act: 0.8997. Min Act: -0.1070

Data Index: 1951781 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8829. Min Act: -0.1123

Data Index: 6830799 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8787. Min Act: -0.0965

Data Index: 7224738 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8757. Min Act: -0.1377

Data Index: 7864514 (Open Web Text)

Max Activating Token Index: 807

Text #4

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8615. Min Act: -0.1092

Data Index: 1775617 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8630. Min Act: -0.1237

Data Index: 8023476 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8437. Min Act: -0.0846

Data Index: 6903614 (Open Web Text)

Max Activating Token Index: 750

Text #7

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8489. Min Act: -0.1157

Data Index: 4634808 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8482. Min Act: -0.1198

Data Index: 6395405 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8465. Min Act: -0.1172

Data Index: 6438755 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8337. Min Act: -0.1143

Data Index: 8032775 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8333. Min Act: -0.1079

Data Index: 6506692 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8369. Min Act: -0.1440

Data Index: 1700133 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8279. Min Act: -0.1588

Data Index: 1779481 (Open Web Text)

Max Activating Token Index: 781

Text #14

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8255. Min Act: -0.1361

Data Index: 5235461 (Open Web Text)

Max Activating Token Index: 752

Text #15

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8317. Min Act: -0.0979

Data Index: 7078861 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8245. Min Act: -0.1174

Data Index: 4614074 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8275. Min Act: -0.1068

Data Index: 6197893 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8269. Min Act: -0.1225

Data Index: 1216905 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8256. Min Act: -0.0888

Data Index: 3801183 (Open Web Text)

Max Activating Token Index: 727