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

Dataset: Open Web Text

Neuron 2346 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: 3.4163. Min Range: -3.4163

Max Act: 3.4163. Min Act: -0.1700

Data Index: 6983973 (Open Web Text)

Max Activating Token Index: 467

Text #1

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.3375. Min Act: -0.1700

Data Index: 4582380 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.3233. Min Act: -0.1700

Data Index: 5326553 (Open Web Text)

Max Activating Token Index: 357

Text #3

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.3072. Min Act: -0.1700

Data Index: 465811 (Open Web Text)

Max Activating Token Index: 294

Text #4

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2333. Min Act: -0.1700

Data Index: 3167694 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2097. Min Act: -0.1700

Data Index: 6633066 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2001. Min Act: -0.1700

Data Index: 3702205 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2005. Min Act: -0.1700

Data Index: 8438539 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2130. Min Act: -0.1700

Data Index: 7794800 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2233. Min Act: -0.1700

Data Index: 5531768 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2100. Min Act: -0.1700

Data Index: 2577189 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1997. Min Act: -0.1700

Data Index: 5998432 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1986. Min Act: -0.1700

Data Index: 578824 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1951. Min Act: -0.1700

Data Index: 7705304 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1965. Min Act: -0.1700

Data Index: 4202730 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2019. Min Act: -0.1700

Data Index: 7290068 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1496. Min Act: -0.1700

Data Index: 2484121 (Open Web Text)

Max Activating Token Index: 215

Text #17

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1620. Min Act: -0.1700

Data Index: 891664 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1532. Min Act: -0.1700

Data Index: 3720118 (Open Web Text)

Max Activating Token Index: 292

Text #19

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1594. Min Act: -0.1700

Data Index: 23097 (Open Web Text)

Max Activating Token Index: 404