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

Dataset: Open Web Text

Neuron 1637 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: 4.3281. Min Range: -4.3281

Max Act: 4.3281. Min Act: -0.1700

Data Index: 6788608 (Open Web Text)

Max Activating Token Index: 785

Text #1

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.2094. Min Act: -0.1700

Data Index: 5473868 (Open Web Text)

Max Activating Token Index: 835

Text #2

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1351. Min Act: -0.1700

Data Index: 5215410 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1219. Min Act: -0.1700

Data Index: 5774980 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0790. Min Act: -0.1700

Data Index: 1116126 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0364. Min Act: -0.1700

Data Index: 7511615 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0539. Min Act: -0.1700

Data Index: 4454423 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0428. Min Act: -0.1700

Data Index: 3383096 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9908. Min Act: -0.1700

Data Index: 3104652 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9995. Min Act: -0.1700

Data Index: 8029031 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0565. Min Act: -0.1700

Data Index: 815285 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9826. Min Act: -0.1700

Data Index: 6250512 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0201. Min Act: -0.1700

Data Index: 8306267 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0016. Min Act: -0.1700

Data Index: 3168202 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9970. Min Act: -0.1700

Data Index: 7692170 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0068. Min Act: -0.1700

Data Index: 7725723 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0106. Min Act: -0.1700

Data Index: 4747591 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9416. Min Act: -0.1700

Data Index: 6686053 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9677. Min Act: -0.1700

Data Index: 4259427 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 4.3281. Min Range: -4.3281

Max Act: 3.9981. Min Act: -0.1700

Data Index: 1154977 (Open Web Text)

Max Activating Token Index: 104