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

Dataset: Open Web Text

Neuron 2518 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: 1.9236. Min Range: -1.9236

Max Act: 1.9236. Min Act: -0.1700

Data Index: 7581476 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8645. Min Act: -0.1700

Data Index: 4540677 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8634. Min Act: -0.1700

Data Index: 1550207 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8622. Min Act: -0.1700

Data Index: 6071371 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8490. Min Act: -0.1700

Data Index: 4442986 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8470. Min Act: -0.1700

Data Index: 5201154 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8363. Min Act: -0.1700

Data Index: 6466097 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8379. Min Act: -0.1700

Data Index: 6111709 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8377. Min Act: -0.1700

Data Index: 2215420 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8299. Min Act: -0.1700

Data Index: 2911647 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8339. Min Act: -0.1700

Data Index: 166702 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8251. Min Act: -0.1700

Data Index: 5301567 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8241. Min Act: -0.1700

Data Index: 3120988 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8269. Min Act: -0.1700

Data Index: 4425051 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8166. Min Act: -0.1700

Data Index: 1009377 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8307. Min Act: -0.1700

Data Index: 685032 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8176. Min Act: -0.1700

Data Index: 1756656 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8106. Min Act: -0.1700

Data Index: 5602624 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8144. Min Act: -0.1700

Data Index: 4428571 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8167. Min Act: -0.1700

Data Index: 8590310 (Open Web Text)

Max Activating Token Index: 998