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

Dataset: Open Web Text

Neuron 874 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: 1.8163. Min Range: -1.8163

Max Act: 1.8163. Min Act: -0.1700

Data Index: 4340575 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7739. Min Act: -0.1700

Data Index: 6977646 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7646. Min Act: -0.1700

Data Index: 4623483 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7623. Min Act: -0.1700

Data Index: 8825740 (Open Web Text)

Max Activating Token Index: 620

Text #4

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7479. Min Act: -0.1700

Data Index: 6335437 (Open Web Text)

Max Activating Token Index: 365

Text #5

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7577. Min Act: -0.1700

Data Index: 8707527 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7288. Min Act: -0.1700

Data Index: 39215 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7362. Min Act: -0.1700

Data Index: 3917521 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7113. Min Act: -0.1700

Data Index: 4944936 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7218. Min Act: -0.1700

Data Index: 2499238 (Open Web Text)

Max Activating Token Index: 184

Text #10

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7114. Min Act: -0.1700

Data Index: 4204972 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7040. Min Act: -0.1700

Data Index: 4899460 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7025. Min Act: -0.1700

Data Index: 8055473 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.7077. Min Act: -0.1700

Data Index: 2256342 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6959. Min Act: -0.1700

Data Index: 6839968 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6892. Min Act: -0.1700

Data Index: 7097571 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6915. Min Act: -0.1700

Data Index: 7638811 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6799. Min Act: -0.1700

Data Index: 4327819 (Open Web Text)

Max Activating Token Index: 935

Text #18

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6807. Min Act: -0.1700

Data Index: 5723339 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 1.8163. Min Range: -1.8163

Max Act: 1.6701. Min Act: -0.1700

Data Index: 79055 (Open Web Text)

Max Activating Token Index: 321