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

Dataset: Open Web Text

Neuron 959 in Layer 3

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: 3.8980. Min Range: -3.8980

Max Act: 3.8980. Min Act: -0.1700

Data Index: 6063725 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.8535. Min Act: -0.1700

Data Index: 1866825 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7941. Min Act: -0.1700

Data Index: 2144784 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.8055. Min Act: -0.1700

Data Index: 6063724 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7169. Min Act: -0.1700

Data Index: 1866823 (Open Web Text)

Max Activating Token Index: 630

Text #5

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7247. Min Act: -0.1700

Data Index: 6063726 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7087. Min Act: -0.1700

Data Index: 493793 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7087. Min Act: -0.1700

Data Index: 1096447 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6349. Min Act: -0.1700

Data Index: 5063501 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5770. Min Act: -0.1700

Data Index: 3900161 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5651. Min Act: -0.1700

Data Index: 5162754 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5682. Min Act: -0.1700

Data Index: 2851108 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5514. Min Act: -0.1700

Data Index: 1621829 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5570. Min Act: -0.1700

Data Index: 3929924 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5080. Min Act: -0.1700

Data Index: 3536697 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5114. Min Act: -0.1700

Data Index: 1621828 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.4797. Min Act: -0.1700

Data Index: 7966247 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.4753. Min Act: -0.1700

Data Index: 7689632 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.4964. Min Act: -0.1700

Data Index: 5966841 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.4455. Min Act: -0.1700

Data Index: 7318487 (Open Web Text)

Max Activating Token Index: 159