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

Dataset: Open Web Text

Neuron 97 in Layer 2

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: 4.5115. Min Range: -4.5115

Max Act: 4.4958. Min Act: -0.1700

Data Index: 1927840 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.5115. Min Act: -0.1700

Data Index: 4027983 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.4207. Min Act: -0.1700

Data Index: 7714249 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3953. Min Act: -0.1697

Data Index: 5849007 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.4042. Min Act: -0.1699

Data Index: 6563791 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.4215. Min Act: -0.1700

Data Index: 3871779 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3594. Min Act: -0.1700

Data Index: 4719532 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3703. Min Act: -0.1700

Data Index: 8126732 (Open Web Text)

Max Activating Token Index: 418

Text #8

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3137. Min Act: -0.1700

Data Index: 1338331 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3489. Min Act: -0.1700

Data Index: 4639448 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3747. Min Act: -0.1700

Data Index: 1717570 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3540. Min Act: -0.1700

Data Index: 26709 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3560. Min Act: -0.1699

Data Index: 2774167 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3201. Min Act: -0.1700

Data Index: 367276 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3210. Min Act: -0.1700

Data Index: 6870586 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3434. Min Act: -0.1700

Data Index: 6944971 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3075. Min Act: -0.1700

Data Index: 3934834 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3277. Min Act: -0.1700

Data Index: 2172944 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.2971. Min Act: -0.1700

Data Index: 5619375 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 4.5115. Min Range: -4.5115

Max Act: 4.3093. Min Act: -0.1700

Data Index: 3672240 (Open Web Text)

Max Activating Token Index: 190