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

Dataset: Open Web Text

Neuron 1332 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: 2.1195. Min Range: -2.1195

Max Act: 2.1172. Min Act: -0.1700

Data Index: 6474306 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.1195. Min Act: -0.1700

Data Index: 4485585 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0777. Min Act: -0.1700

Data Index: 2783448 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0533. Min Act: -0.1700

Data Index: 7712520 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0509. Min Act: -0.1700

Data Index: 2699222 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0361. Min Act: -0.1700

Data Index: 4886089 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0139. Min Act: -0.1700

Data Index: 8055957 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0172. Min Act: -0.1700

Data Index: 3617850 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0273. Min Act: -0.1700

Data Index: 1667073 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0047. Min Act: -0.1700

Data Index: 3534381 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.1195. Min Range: -2.1195

Max Act: 1.9978. Min Act: -0.1700

Data Index: 3215805 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0110. Min Act: -0.1700

Data Index: 5009212 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0121. Min Act: -0.1700

Data Index: 7430556 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0001. Min Act: -0.1700

Data Index: 8580591 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0115. Min Act: -0.1700

Data Index: 6936143 (Open Web Text)

Max Activating Token Index: 216

Text #15

Max Range: 2.1195. Min Range: -2.1195

Max Act: 1.9962. Min Act: -0.1700

Data Index: 5744333 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0043. Min Act: -0.1700

Data Index: 2290930 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0087. Min Act: -0.1700

Data Index: 167631 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 2.1195. Min Range: -2.1195

Max Act: 2.0089. Min Act: -0.1700

Data Index: 20054 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 2.1195. Min Range: -2.1195

Max Act: 1.9935. Min Act: -0.1700

Data Index: 2111615 (Open Web Text)

Max Activating Token Index: 51