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

Dataset: Open Web Text

Neuron 484 in Layer 6

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: 3.2172. Min Range: -3.2172

Max Act: 3.2172. Min Act: -0.1700

Data Index: 4243114 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1165048 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.0940. Min Act: -0.1700

Data Index: 8626741 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.0682. Min Act: -0.1700

Data Index: 2262566 (Open Web Text)

Max Activating Token Index: 339

Text #4

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.0315. Min Act: -0.1700

Data Index: 61957 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.0133. Min Act: -0.1700

Data Index: 2805320 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 3.2172. Min Range: -3.2172

Max Act: 3.0025. Min Act: -0.1700

Data Index: 6321488 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9343. Min Act: -0.1700

Data Index: 2368996 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9924. Min Act: -0.1700

Data Index: 893832 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9604. Min Act: -0.1700

Data Index: 30935 (Open Web Text)

Max Activating Token Index: 897

Text #10

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9577. Min Act: -0.1700

Data Index: 6573475 (Open Web Text)

Max Activating Token Index: 733

Text #11

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9326. Min Act: -0.1700

Data Index: 2481996 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9629. Min Act: -0.1700

Data Index: 4586972 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9418. Min Act: -0.1700

Data Index: 300576 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9457. Min Act: -0.1700

Data Index: 6333552 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9610. Min Act: -0.1700

Data Index: 765866 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9275. Min Act: -0.1700

Data Index: 920923 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9344. Min Act: -0.1700

Data Index: 2035531 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9124. Min Act: -0.1700

Data Index: 6935126 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 3.2172. Min Range: -3.2172

Max Act: 2.9223. Min Act: -0.1700

Data Index: 6116007 (Open Web Text)

Max Activating Token Index: 328