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

Dataset: Open Web Text

Neuron 135 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: 3.5866. Min Range: -3.5866

Max Act: 3.5866. Min Act: -0.1700

Data Index: 3920720 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5461. Min Act: -0.1700

Data Index: 8589153 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5440. Min Act: -0.1700

Data Index: 6503056 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5505. Min Act: -0.1700

Data Index: 7363420 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5406. Min Act: -0.1700

Data Index: 6626901 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5470. Min Act: -0.1700

Data Index: 5468768 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5271. Min Act: -0.1700

Data Index: 4204417 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5251. Min Act: -0.1700

Data Index: 6389725 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5086. Min Act: -0.1700

Data Index: 4475520 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5003. Min Act: -0.1700

Data Index: 500556 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5162. Min Act: -0.1700

Data Index: 1181979 (Open Web Text)

Max Activating Token Index: 687

Text #11

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5111. Min Act: -0.1700

Data Index: 4908647 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.5128. Min Act: -0.1700

Data Index: 739663 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4911. Min Act: -0.1700

Data Index: 4676245 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4671. Min Act: -0.1700

Data Index: 4303690 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4696. Min Act: -0.1700

Data Index: 3120732 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4672. Min Act: -0.1700

Data Index: 6137330 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4637. Min Act: -0.1700

Data Index: 7387911 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4584. Min Act: -0.1700

Data Index: 1345676 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.4582. Min Act: -0.1700

Data Index: 4436269 (Open Web Text)

Max Activating Token Index: 130