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

Dataset: Open Web Text

Neuron 1508 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: 4.1034. Min Range: -4.1034

Max Act: 4.1034. Min Act: -0.1700

Data Index: 3852503 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0524. Min Act: -0.1700

Data Index: 3617738 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0690. Min Act: -0.1700

Data Index: 7090037 (Open Web Text)

Max Activating Token Index: 790

Text #3

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0587. Min Act: -0.1700

Data Index: 2997092 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0983. Min Act: -0.1700

Data Index: 498696 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0316. Min Act: -0.1700

Data Index: 2340587 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0094. Min Act: -0.1700

Data Index: 7539718 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0765. Min Act: -0.1700

Data Index: 7776235 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0560. Min Act: -0.1700

Data Index: 7993859 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0356. Min Act: -0.1700

Data Index: 952436 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0288. Min Act: -0.1700

Data Index: 2255691 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0059. Min Act: -0.1700

Data Index: 5986063 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9823. Min Act: -0.1700

Data Index: 2341437 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0236. Min Act: -0.1700

Data Index: 2997919 (Open Web Text)

Max Activating Token Index: 614

Text #14

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9987. Min Act: -0.1700

Data Index: 2159338 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0109. Min Act: -0.1700

Data Index: 8726192 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0093. Min Act: -0.1700

Data Index: 2466422 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9699. Min Act: -0.1700

Data Index: 6648627 (Open Web Text)

Max Activating Token Index: 637

Text #18

Max Range: 4.1034. Min Range: -4.1034

Max Act: 3.9663. Min Act: -0.1700

Data Index: 285708 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 4.1034. Min Range: -4.1034

Max Act: 4.0061. Min Act: -0.1700

Data Index: 3573738 (Open Web Text)

Max Activating Token Index: 152