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

Dataset: Open Web Text

Neuron 1538 in Layer 4

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: 4.2084. Min Range: -4.2084

Max Act: 4.2084. Min Act: -0.1700

Data Index: 8514217 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.1122. Min Act: -0.1700

Data Index: 6342518 (Open Web Text)

Max Activating Token Index: 822

Text #2

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.1001. Min Act: -0.1700

Data Index: 1356758 (Open Web Text)

Max Activating Token Index: 943

Text #3

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0499. Min Act: -0.1700

Data Index: 6026534 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0856. Min Act: -0.1700

Data Index: 242256 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0242. Min Act: -0.1700

Data Index: 7688736 (Open Web Text)

Max Activating Token Index: 996

Text #6

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0004. Min Act: -0.1700

Data Index: 5726121 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9946. Min Act: -0.1700

Data Index: 3762125 (Open Web Text)

Max Activating Token Index: 662

Text #8

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0003. Min Act: -0.1700

Data Index: 7010392 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9788. Min Act: -0.1700

Data Index: 4421743 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9692. Min Act: -0.1700

Data Index: 5853237 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9773. Min Act: -0.1700

Data Index: 2811689 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9409. Min Act: -0.1700

Data Index: 91305 (Open Web Text)

Max Activating Token Index: 154

Text #13

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9353. Min Act: -0.1700

Data Index: 2154875 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9176. Min Act: -0.1700

Data Index: 3630673 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9105. Min Act: -0.1700

Data Index: 7694708 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8874. Min Act: -0.1700

Data Index: 8090791 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8578. Min Act: -0.1700

Data Index: 1187690 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9024. Min Act: -0.1700

Data Index: 4094805 (Open Web Text)

Max Activating Token Index: 288

Text #19

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8860. Min Act: -0.1700

Data Index: 8352939 (Open Web Text)

Max Activating Token Index: 379