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

Dataset: Open Web Text

Neuron 593 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: 4.9417. Min Range: -4.9417

Max Act: 4.9417. Min Act: -0.1700

Data Index: 6339202 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.9171. Min Act: -0.1700

Data Index: 7326862 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8226. Min Act: -0.1700

Data Index: 8820945 (Open Web Text)

Max Activating Token Index: 782

Text #3

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8760. Min Act: -0.1700

Data Index: 7405570 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8302. Min Act: -0.1700

Data Index: 5087917 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8038. Min Act: -0.1700

Data Index: 5950122 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8228. Min Act: -0.1700

Data Index: 5701407 (Open Web Text)

Max Activating Token Index: 681

Text #7

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8320. Min Act: -0.1700

Data Index: 4545286 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8090. Min Act: -0.1700

Data Index: 5192335 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8154. Min Act: -0.1700

Data Index: 1644036 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8329. Min Act: -0.1700

Data Index: 8605533 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8071. Min Act: -0.1700

Data Index: 2140796 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.7885. Min Act: -0.1700

Data Index: 5174171 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.7898. Min Act: -0.1700

Data Index: 2842276 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8330. Min Act: -0.1700

Data Index: 4810507 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8018. Min Act: -0.1700

Data Index: 3978554 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.8214. Min Act: -0.1700

Data Index: 6484312 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.7307. Min Act: -0.1700

Data Index: 4235161 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.7636. Min Act: -0.1700

Data Index: 1439315 (Open Web Text)

Max Activating Token Index: 510

Text #19

Max Range: 4.9417. Min Range: -4.9417

Max Act: 4.7124. Min Act: -0.1700

Data Index: 5787605 (Open Web Text)

Max Activating Token Index: 336