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

Dataset: Open Web Text

Neuron 941 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: 3.0108. Min Range: -3.0108

Max Act: 3.0108. Min Act: -0.1700

Data Index: 3433067 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.9444. Min Act: -0.1700

Data Index: 3222946 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.9035. Min Act: -0.1700

Data Index: 6244124 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.8036. Min Act: -0.1700

Data Index: 3354926 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7742. Min Act: -0.1700

Data Index: 4694436 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7637. Min Act: -0.1700

Data Index: 2572277 (Open Web Text)

Max Activating Token Index: 380

Text #6

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7345. Min Act: -0.1700

Data Index: 4254283 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7270. Min Act: -0.1700

Data Index: 6957419 (Open Web Text)

Max Activating Token Index: 819

Text #8

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7520. Min Act: -0.1700

Data Index: 2065341 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7327. Min Act: -0.1700

Data Index: 3580042 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7099. Min Act: -0.1700

Data Index: 5085024 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7171. Min Act: -0.1700

Data Index: 6761800 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6714. Min Act: -0.1700

Data Index: 2290430 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6718. Min Act: -0.1700

Data Index: 5839035 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6951. Min Act: -0.1700

Data Index: 1919865 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7099. Min Act: -0.1700

Data Index: 1725397 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7102. Min Act: -0.1700

Data Index: 5826031 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6718. Min Act: -0.1700

Data Index: 2416141 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6823. Min Act: -0.1700

Data Index: 8019376 (Open Web Text)

Max Activating Token Index: 119

Text #19

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6812. Min Act: -0.1700

Data Index: 6823841 (Open Web Text)

Max Activating Token Index: 1013