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

Dataset: Open Web Text

Neuron 121 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: 3.7788. Min Range: -3.7788

Max Act: 3.7672. Min Act: -0.1700

Data Index: 1851633 (Open Web Text)

Max Activating Token Index: 649

Text #1

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7788. Min Act: -0.1700

Data Index: 8275176 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7224. Min Act: -0.1700

Data Index: 305288 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7250. Min Act: -0.1700

Data Index: 2415282 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7442. Min Act: -0.1700

Data Index: 8591904 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6986. Min Act: -0.1700

Data Index: 160734 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7230. Min Act: -0.1700

Data Index: 4953518 (Open Web Text)

Max Activating Token Index: 867

Text #7

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7136. Min Act: -0.1700

Data Index: 3072779 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7233. Min Act: -0.1700

Data Index: 6744081 (Open Web Text)

Max Activating Token Index: 898

Text #9

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.7082. Min Act: -0.1700

Data Index: 1466376 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6819. Min Act: -0.1700

Data Index: 6080786 (Open Web Text)

Max Activating Token Index: 748

Text #11

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6767. Min Act: -0.1700

Data Index: 1229259 (Open Web Text)

Max Activating Token Index: 212

Text #12

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6552. Min Act: -0.1700

Data Index: 5968264 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6596. Min Act: -0.1700

Data Index: 3480108 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6687. Min Act: -0.1700

Data Index: 5428439 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6581. Min Act: -0.1700

Data Index: 3960662 (Open Web Text)

Max Activating Token Index: 754

Text #16

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6336. Min Act: -0.1700

Data Index: 2183995 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6612. Min Act: -0.1700

Data Index: 5103293 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6408. Min Act: -0.1700

Data Index: 1229529 (Open Web Text)

Max Activating Token Index: 728

Text #19

Max Range: 3.7788. Min Range: -3.7788

Max Act: 3.6329. Min Act: -0.1700

Data Index: 5968263 (Open Web Text)

Max Activating Token Index: 906