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

Dataset: Open Web Text

Neuron 189 in Layer 5

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: 5.1226. Min Range: -5.1226

Max Act: 5.1226. Min Act: -0.1700

Data Index: 2989485 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0924. Min Act: -0.1700

Data Index: 2458899 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0398. Min Act: -0.1700

Data Index: 5257060 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0210. Min Act: -0.1700

Data Index: 1580139 (Open Web Text)

Max Activating Token Index: 1001

Text #4

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9986. Min Act: -0.1700

Data Index: 4386486 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0263. Min Act: -0.1700

Data Index: 5578260 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9828. Min Act: -0.1700

Data Index: 6415794 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0004. Min Act: -0.1700

Data Index: 4611962 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 5.1226. Min Range: -5.1226

Max Act: 5.0034. Min Act: -0.1700

Data Index: 4740753 (Open Web Text)

Max Activating Token Index: 681

Text #9

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9881. Min Act: -0.1700

Data Index: 2518549 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9434. Min Act: -0.1700

Data Index: 7203487 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9396. Min Act: -0.1700

Data Index: 4472456 (Open Web Text)

Max Activating Token Index: 886

Text #12

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9504. Min Act: -0.1700

Data Index: 8627054 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9627. Min Act: -0.1700

Data Index: 7692613 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9232. Min Act: -0.1700

Data Index: 88017 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9307. Min Act: -0.1700

Data Index: 6044059 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9273. Min Act: -0.1700

Data Index: 4340671 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9177. Min Act: -0.1700

Data Index: 6844542 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9356. Min Act: -0.1700

Data Index: 2469897 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 5.1226. Min Range: -5.1226

Max Act: 4.9091. Min Act: -0.1700

Data Index: 7703185 (Open Web Text)

Max Activating Token Index: 275