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

Dataset: Open Web Text

Neuron 806 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: 3.7960. Min Range: -3.7960

Max Act: 3.7960. Min Act: -0.1700

Data Index: 4223006 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.7304. Min Act: -0.1700

Data Index: 2491259 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.7353. Min Act: -0.1700

Data Index: 6562767 (Open Web Text)

Max Activating Token Index: 220

Text #3

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.7244. Min Act: -0.1700

Data Index: 2805721 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6367. Min Act: -0.1700

Data Index: 6028599 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6375. Min Act: -0.1700

Data Index: 2332486 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6666. Min Act: -0.1700

Data Index: 8587121 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6840. Min Act: -0.1700

Data Index: 3772627 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6363. Min Act: -0.1700

Data Index: 6279061 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6066. Min Act: -0.1700

Data Index: 242747 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6325. Min Act: -0.1700

Data Index: 6523815 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6484. Min Act: -0.1700

Data Index: 4188088 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6338. Min Act: -0.1700

Data Index: 3509471 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6339. Min Act: -0.1700

Data Index: 3627072 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.5819. Min Act: -0.1700

Data Index: 3611762 (Open Web Text)

Max Activating Token Index: 570

Text #15

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6005. Min Act: -0.1700

Data Index: 2455672 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6126. Min Act: -0.1700

Data Index: 7924112 (Open Web Text)

Max Activating Token Index: 523

Text #17

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.5913. Min Act: -0.1700

Data Index: 4430315 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.6096. Min Act: -0.1700

Data Index: 3164501 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 3.7960. Min Range: -3.7960

Max Act: 3.5825. Min Act: -0.1700

Data Index: 6082937 (Open Web Text)

Max Activating Token Index: 950