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

Dataset: Open Web Text

Neuron 13 in Layer 2

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: 3.3633. Min Range: -3.3633

Max Act: 3.3633. Min Act: -0.1700

Data Index: 4341084 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.3633. Min Range: -3.3633

Max Act: 3.0235. Min Act: -0.1672

Data Index: 6883772 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 3.3633. Min Range: -3.3633

Max Act: 3.0191. Min Act: -0.1698

Data Index: 2243025 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 3.3633. Min Range: -3.3633

Max Act: 3.0131. Min Act: -0.1700

Data Index: 1357031 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9916. Min Act: -0.1700

Data Index: 6068157 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9923. Min Act: -0.1700

Data Index: 5548427 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9968. Min Act: -0.1695

Data Index: 2243030 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 3.3633. Min Range: -3.3633

Max Act: 3.0000. Min Act: -0.1700

Data Index: 6883774 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9965. Min Act: -0.1685

Data Index: 6883773 (Open Web Text)

Max Activating Token Index: 605

Text #9

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9660. Min Act: -0.1698

Data Index: 6883771 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9432. Min Act: -0.1699

Data Index: 2243026 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9272. Min Act: -0.1700

Data Index: 3673171 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9298. Min Act: -0.1649

Data Index: 8107850 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9395. Min Act: -0.1700

Data Index: 8170682 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9310. Min Act: -0.1700

Data Index: 2655624 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9174. Min Act: -0.1700

Data Index: 1041132 (Open Web Text)

Max Activating Token Index: 131

Text #16

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9216. Min Act: -0.1700

Data Index: 5019125 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9096. Min Act: -0.1700

Data Index: 8107845 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.9055. Min Act: -0.1700

Data Index: 674513 (Open Web Text)

Max Activating Token Index: 126

Text #19

Max Range: 3.3633. Min Range: -3.3633

Max Act: 2.8913. Min Act: -0.1700

Data Index: 3245402 (Open Web Text)

Max Activating Token Index: 891