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

Dataset: Open Web Text

Neuron 2242 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: 3.8928. Min Range: -3.8928

Max Act: 3.8928. Min Act: -0.1700

Data Index: 692583 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8324. Min Act: -0.1700

Data Index: 6336771 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8202. Min Act: -0.1700

Data Index: 6224464 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8465. Min Act: -0.1700

Data Index: 7772674 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8393. Min Act: -0.1700

Data Index: 8169609 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8250. Min Act: -0.1700

Data Index: 5866366 (Open Web Text)

Max Activating Token Index: 652

Text #6

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.8394. Min Act: -0.1700

Data Index: 3176116 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7628. Min Act: -0.1700

Data Index: 6599037 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7850. Min Act: -0.1700

Data Index: 4217480 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7575. Min Act: -0.1700

Data Index: 3617725 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7984. Min Act: -0.1700

Data Index: 2922176 (Open Web Text)

Max Activating Token Index: 986

Text #11

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7792. Min Act: -0.1700

Data Index: 3413202 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7298. Min Act: -0.1700

Data Index: 6893248 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7436. Min Act: -0.1700

Data Index: 2244870 (Open Web Text)

Max Activating Token Index: 138

Text #14

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7226. Min Act: -0.1700

Data Index: 4495819 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7433. Min Act: -0.1700

Data Index: 8381367 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7369. Min Act: -0.1700

Data Index: 2616692 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7431. Min Act: -0.1700

Data Index: 77548 (Open Web Text)

Max Activating Token Index: 794

Text #18

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.7514. Min Act: -0.1700

Data Index: 2139131 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 3.8928. Min Range: -3.8928

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1048244 (Open Web Text)

Max Activating Token Index: 512