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

Dataset: Open Web Text

Neuron 2262 in Layer 0

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: 3.6318. Min Range: -3.6318

Max Act: 3.6318. Min Act: -0.1700

Data Index: 4775637 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.5345. Min Act: -0.1700

Data Index: 2286002 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.5204. Min Act: -0.1700

Data Index: 8140345 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.5037. Min Act: -0.1700

Data Index: 8148354 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4929. Min Act: -0.1700

Data Index: 2970844 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4941. Min Act: -0.1700

Data Index: 6646969 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4707. Min Act: -0.1700

Data Index: 4253684 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4864. Min Act: -0.1700

Data Index: 655561 (Open Web Text)

Max Activating Token Index: 415

Text #8

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4722. Min Act: -0.1700

Data Index: 2351117 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4601. Min Act: -0.1700

Data Index: 5774817 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4583. Min Act: -0.1700

Data Index: 4323456 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4517. Min Act: -0.1700

Data Index: 302763 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4346. Min Act: -0.1700

Data Index: 7131781 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4574. Min Act: -0.1700

Data Index: 7584256 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4423. Min Act: -0.1700

Data Index: 4563294 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4015. Min Act: -0.1700

Data Index: 5463935 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4097. Min Act: -0.1700

Data Index: 1271940 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4058. Min Act: -0.1700

Data Index: 4376116 (Open Web Text)

Max Activating Token Index: 458

Text #18

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4233. Min Act: -0.1700

Data Index: 4520790 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.6318. Min Range: -3.6318

Max Act: 3.4222. Min Act: -0.1700

Data Index: 8086174 (Open Web Text)

Max Activating Token Index: 72