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

Dataset: Open Web Text

Neuron 2239 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: 3.3410. Min Range: -3.3410

Max Act: 3.3410. Min Act: -0.1700

Data Index: 6883454 (Open Web Text)

Max Activating Token Index: 913

Text #1

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3054. Min Act: -0.1700

Data Index: 5791002 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2878. Min Act: -0.1700

Data Index: 4094213 (Open Web Text)

Max Activating Token Index: 365

Text #3

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2875. Min Act: -0.1700

Data Index: 1226385 (Open Web Text)

Max Activating Token Index: 121

Text #4

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2897. Min Act: -0.1700

Data Index: 3087058 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2644. Min Act: -0.1700

Data Index: 5782681 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2686. Min Act: -0.1700

Data Index: 1317682 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2538. Min Act: -0.1700

Data Index: 3012100 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2458. Min Act: -0.1700

Data Index: 785132 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2417. Min Act: -0.1700

Data Index: 3002659 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2302. Min Act: -0.1700

Data Index: 2473103 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2234. Min Act: -0.1700

Data Index: 6987460 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2020. Min Act: -0.1700

Data Index: 7014915 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2203. Min Act: -0.1700

Data Index: 399047 (Open Web Text)

Max Activating Token Index: 293

Text #14

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2057. Min Act: -0.1700

Data Index: 3759248 (Open Web Text)

Max Activating Token Index: 250

Text #15

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1959. Min Act: -0.1700

Data Index: 7293167 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2047. Min Act: -0.1700

Data Index: 3922931 (Open Web Text)

Max Activating Token Index: 179

Text #17

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1973. Min Act: -0.1700

Data Index: 6003742 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1906. Min Act: -0.1700

Data Index: 1142780 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1636. Min Act: -0.1700

Data Index: 1255695 (Open Web Text)

Max Activating Token Index: 66