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

Dataset: Open Web Text

Neuron 2149 in Layer 6

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: 3.4327. Min Range: -3.4327

Max Act: 3.4327. Min Act: -0.1700

Data Index: 8231230 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.3920. Min Act: -0.1700

Data Index: 6373913 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.3721. Min Act: -0.1700

Data Index: 3016216 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.3382. Min Act: -0.1700

Data Index: 6960919 (Open Web Text)

Max Activating Token Index: 293

Text #4

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2843. Min Act: -0.1700

Data Index: 1160213 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2888. Min Act: -0.1700

Data Index: 5889005 (Open Web Text)

Max Activating Token Index: 864

Text #6

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2796. Min Act: -0.1700

Data Index: 6256769 (Open Web Text)

Max Activating Token Index: 977

Text #7

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.3075. Min Act: -0.1700

Data Index: 2823835 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2853. Min Act: -0.1700

Data Index: 3670315 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2874. Min Act: -0.1700

Data Index: 3636927 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2751. Min Act: -0.1700

Data Index: 4929623 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2643. Min Act: -0.1700

Data Index: 3587360 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2526. Min Act: -0.1700

Data Index: 4331020 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2421. Min Act: -0.1700

Data Index: 1021047 (Open Web Text)

Max Activating Token Index: 664

Text #14

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2312. Min Act: -0.1700

Data Index: 3681153 (Open Web Text)

Max Activating Token Index: 347

Text #15

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2322. Min Act: -0.1700

Data Index: 8750190 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.1974. Min Act: -0.1700

Data Index: 4683417 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2377. Min Act: -0.1700

Data Index: 7423528 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2093. Min Act: -0.1700

Data Index: 6843040 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 3.4327. Min Range: -3.4327

Max Act: 3.2149. Min Act: -0.1700

Data Index: 3198840 (Open Web Text)

Max Activating Token Index: 387