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

Dataset: Open Web Text

Neuron 2367 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: 4.4108. Min Range: -4.4108

Max Act: 4.4108. Min Act: -0.1700

Data Index: 1335091 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.3226. Min Act: -0.1700

Data Index: 2353723 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.3279. Min Act: -0.1700

Data Index: 3829245 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2767. Min Act: -0.1700

Data Index: 1703060 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2866. Min Act: -0.1700

Data Index: 5562056 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2524. Min Act: -0.1700

Data Index: 6689211 (Open Web Text)

Max Activating Token Index: 943

Text #6

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2394. Min Act: -0.1700

Data Index: 4173382 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2348. Min Act: -0.1700

Data Index: 7528829 (Open Web Text)

Max Activating Token Index: 666

Text #8

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2369. Min Act: -0.1700

Data Index: 8568167 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1836. Min Act: -0.1700

Data Index: 4085222 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.2095. Min Act: -0.1700

Data Index: 1232957 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1879. Min Act: -0.1700

Data Index: 4451561 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1666. Min Act: -0.1700

Data Index: 1820185 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1608. Min Act: -0.1700

Data Index: 8390866 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1831. Min Act: -0.1700

Data Index: 4219072 (Open Web Text)

Max Activating Token Index: 697

Text #15

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1228. Min Act: -0.1700

Data Index: 3823342 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1567. Min Act: -0.1700

Data Index: 4176337 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1458. Min Act: -0.1700

Data Index: 1612999 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1193. Min Act: -0.1700

Data Index: 3310839 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 4.4108. Min Range: -4.4108

Max Act: 4.1314. Min Act: -0.1700

Data Index: 1185675 (Open Web Text)

Max Activating Token Index: 472