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

Dataset: Open Web Text

Neuron 232 in Layer 4

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: 1.8682. Min Range: -1.8682

Max Act: 1.8547. Min Act: -0.1700

Data Index: 4187318 (Open Web Text)

Max Activating Token Index: 341

Text #1

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.8682. Min Act: -0.1700

Data Index: 781959 (Open Web Text)

Max Activating Token Index: 278

Text #2

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7820. Min Act: -0.1700

Data Index: 6228874 (Open Web Text)

Max Activating Token Index: 301

Text #3

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7660. Min Act: -0.1700

Data Index: 437808 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7728. Min Act: -0.1700

Data Index: 5834469 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7704. Min Act: -0.1700

Data Index: 247642 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7610. Min Act: -0.1700

Data Index: 5357165 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7415. Min Act: -0.1700

Data Index: 1721126 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7291. Min Act: -0.1700

Data Index: 144907 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7412. Min Act: -0.1700

Data Index: 2554402 (Open Web Text)

Max Activating Token Index: 328

Text #10

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7061. Min Act: -0.1700

Data Index: 7155084 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7202. Min Act: -0.1700

Data Index: 2222460 (Open Web Text)

Max Activating Token Index: 311

Text #12

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7189. Min Act: -0.1700

Data Index: 5459336 (Open Web Text)

Max Activating Token Index: 350

Text #13

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7081. Min Act: -0.1700

Data Index: 2430171 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7071. Min Act: -0.1700

Data Index: 2875780 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.6942. Min Act: -0.1700

Data Index: 6445235 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7083. Min Act: -0.1700

Data Index: 5567698 (Open Web Text)

Max Activating Token Index: 300

Text #17

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.7103. Min Act: -0.1700

Data Index: 4414561 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.6891. Min Act: -0.1700

Data Index: 3570178 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 1.8682. Min Range: -1.8682

Max Act: 1.6943. Min Act: -0.1700

Data Index: 4463036 (Open Web Text)

Max Activating Token Index: 316