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

Dataset: Open Web Text

Neuron 1665 in Layer 1

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: 7.3157. Min Range: -7.3157

Max Act: 7.3157. Min Act: -0.1700

Data Index: 1758231 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.2273. Min Act: -0.1700

Data Index: 8472721 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1958. Min Act: -0.1700

Data Index: 3840384 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1315. Min Act: -0.1700

Data Index: 6627912 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1253. Min Act: -0.1700

Data Index: 6954278 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1685. Min Act: -0.1700

Data Index: 5788882 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1347. Min Act: -0.1700

Data Index: 272190 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1816. Min Act: -0.1700

Data Index: 130643 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1358. Min Act: -0.1700

Data Index: 4063878 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1663. Min Act: -0.1700

Data Index: 8690110 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0731. Min Act: -0.1700

Data Index: 1753274 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1004. Min Act: -0.1700

Data Index: 4216696 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0771. Min Act: -0.1700

Data Index: 4377870 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1181. Min Act: -0.1700

Data Index: 1751028 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0705. Min Act: -0.1700

Data Index: 1853283 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0801. Min Act: -0.1700

Data Index: 4823061 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1155. Min Act: -0.1700

Data Index: 5784235 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0955. Min Act: -0.1700

Data Index: 2396476 (Open Web Text)

Max Activating Token Index: 276

Text #18

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.1167. Min Act: -0.1700

Data Index: 3790840 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 7.3157. Min Range: -7.3157

Max Act: 7.0769. Min Act: -0.1700

Data Index: 6614603 (Open Web Text)

Max Activating Token Index: 164