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

Dataset: Open Web Text

Neuron 45 in Layer 6

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: 6.6164. Min Range: -6.6164

Max Act: 6.6157. Min Act: -0.1700

Data Index: 4456951 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.6164. Min Act: -0.1700

Data Index: 8527731 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.4878. Min Act: -0.1700

Data Index: 8553175 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.4205. Min Act: -0.1700

Data Index: 4730291 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.4280. Min Act: -0.1700

Data Index: 3503983 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.3476. Min Act: -0.1700

Data Index: 6030295 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.3824. Min Act: -0.1700

Data Index: 2926126 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.3133. Min Act: -0.1700

Data Index: 1455907 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.2764. Min Act: -0.1700

Data Index: 6933027 (Open Web Text)

Max Activating Token Index: 196

Text #9

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.2614. Min Act: -0.1700

Data Index: 4338072 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.2995. Min Act: -0.1700

Data Index: 7358721 (Open Web Text)

Max Activating Token Index: 717

Text #11

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.2668. Min Act: -0.1700

Data Index: 6319485 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1682. Min Act: -0.1700

Data Index: 849757 (Open Web Text)

Max Activating Token Index: 962

Text #13

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1878. Min Act: -0.1700

Data Index: 8296529 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1897. Min Act: -0.1700

Data Index: 3952771 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1457. Min Act: -0.1700

Data Index: 531075 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1844. Min Act: -0.1700

Data Index: 7229522 (Open Web Text)

Max Activating Token Index: 116

Text #17

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1948. Min Act: -0.1700

Data Index: 2061076 (Open Web Text)

Max Activating Token Index: 603

Text #18

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1871. Min Act: -0.1700

Data Index: 4901097 (Open Web Text)

Max Activating Token Index: 308

Text #19

Max Range: 6.6164. Min Range: -6.6164

Max Act: 6.1654. Min Act: -0.1700

Data Index: 4468732 (Open Web Text)

Max Activating Token Index: 479