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

Dataset: Open Web Text

Neuron 900 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: 3.0780. Min Range: -3.0780

Max Act: 3.0780. Min Act: -0.1700

Data Index: 7186482 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0376. Min Act: -0.1700

Data Index: 7915171 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 3.0780. Min Range: -3.0780

Max Act: 3.0243. Min Act: -0.1700

Data Index: 3059265 (Open Web Text)

Max Activating Token Index: 273

Text #3

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9994. Min Act: -0.1700

Data Index: 5185271 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9769. Min Act: -0.1700

Data Index: 8403445 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9881. Min Act: -0.1700

Data Index: 6792083 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9806. Min Act: -0.1700

Data Index: 6792078 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9991. Min Act: -0.1700

Data Index: 3395755 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9893. Min Act: -0.1700

Data Index: 1194730 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9834. Min Act: -0.1700

Data Index: 7024938 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9520. Min Act: -0.1700

Data Index: 3576111 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9401. Min Act: -0.1700

Data Index: 3009689 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9364. Min Act: -0.1700

Data Index: 2823900 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9373. Min Act: -0.1700

Data Index: 2823902 (Open Web Text)

Max Activating Token Index: 214

Text #14

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9407. Min Act: -0.1700

Data Index: 2328709 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9422. Min Act: -0.1700

Data Index: 3061062 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9435. Min Act: -0.1700

Data Index: 3647336 (Open Web Text)

Max Activating Token Index: 235

Text #17

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9223. Min Act: -0.1700

Data Index: 6792082 (Open Web Text)

Max Activating Token Index: 262

Text #18

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.8959. Min Act: -0.1700

Data Index: 6792081 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 3.0780. Min Range: -3.0780

Max Act: 2.9102. Min Act: -0.1700

Data Index: 7281265 (Open Web Text)

Max Activating Token Index: 203