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

Dataset: Open Web Text

Neuron 934 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: 1.8172. Min Range: -1.8172

Max Act: 1.8172. Min Act: -0.1700

Data Index: 4908455 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7791. Min Act: -0.1700

Data Index: 6644248 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7709. Min Act: -0.1700

Data Index: 6644247 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7656. Min Act: -0.1700

Data Index: 8533783 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7533. Min Act: -0.1700

Data Index: 8766605 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7251. Min Act: -0.1700

Data Index: 6564008 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7379. Min Act: -0.1700

Data Index: 6264296 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7306. Min Act: -0.1700

Data Index: 3423678 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7302. Min Act: -0.1700

Data Index: 1202738 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7169. Min Act: -0.1700

Data Index: 4611300 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6910. Min Act: -0.1700

Data Index: 6945948 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6987. Min Act: -0.1700

Data Index: 5130187 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6970. Min Act: -0.1700

Data Index: 7033988 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7048. Min Act: -0.1700

Data Index: 7452467 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.7062. Min Act: -0.1700

Data Index: 8050335 (Open Web Text)

Max Activating Token Index: 66

Text #15

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6985. Min Act: -0.1700

Data Index: 6781284 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6978. Min Act: -0.1700

Data Index: 348754 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6997. Min Act: -0.1700

Data Index: 5150592 (Open Web Text)

Max Activating Token Index: 624

Text #18

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6767. Min Act: -0.1700

Data Index: 1474847 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.8172. Min Range: -1.8172

Max Act: 1.6722. Min Act: -0.1700

Data Index: 6917785 (Open Web Text)

Max Activating Token Index: 691