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

Dataset: Open Web Text

Neuron 1285 in Layer 4

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: 3.9819. Min Range: -3.9819

Max Act: 3.9819. Min Act: -0.1700

Data Index: 2164921 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.9233. Min Act: -0.1700

Data Index: 4334028 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.8413. Min Act: -0.1700

Data Index: 3214441 (Open Web Text)

Max Activating Token Index: 367

Text #3

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.8518. Min Act: -0.1700

Data Index: 8508534 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7795. Min Act: -0.1700

Data Index: 7390805 (Open Web Text)

Max Activating Token Index: 705

Text #5

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7808. Min Act: -0.1700

Data Index: 2590650 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7954. Min Act: -0.1700

Data Index: 102075 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7819. Min Act: -0.1700

Data Index: 525944 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7142. Min Act: -0.1700

Data Index: 3214438 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7507. Min Act: -0.1700

Data Index: 5775641 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7543. Min Act: -0.1700

Data Index: 2781451 (Open Web Text)

Max Activating Token Index: 210

Text #11

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7313. Min Act: -0.1700

Data Index: 8508531 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7137. Min Act: -0.1700

Data Index: 1292510 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7048. Min Act: -0.1700

Data Index: 102078 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.6814. Min Act: -0.1700

Data Index: 4195064 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7020. Min Act: -0.1700

Data Index: 3627702 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7167. Min Act: -0.1700

Data Index: 7390803 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.7092. Min Act: -0.1700

Data Index: 1295960 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.6851. Min Act: -0.1700

Data Index: 2781447 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 3.9819. Min Range: -3.9819

Max Act: 3.6888. Min Act: -0.1700

Data Index: 2590652 (Open Web Text)

Max Activating Token Index: 880