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

Dataset: Open Web Text

Neuron 2627 in Layer 3

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: 3.4324. Min Range: -3.4324

Max Act: 3.4314. Min Act: -0.1700

Data Index: 2539882 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3992. Min Act: -0.1700

Data Index: 257524 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.4324. Min Act: -0.1700

Data Index: 3495251 (Open Web Text)

Max Activating Token Index: 386

Text #3

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3855. Min Act: -0.1700

Data Index: 4089049 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3895. Min Act: -0.1700

Data Index: 6681027 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3764. Min Act: -0.1700

Data Index: 561563 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3532. Min Act: -0.1700

Data Index: 5669767 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3550. Min Act: -0.1700

Data Index: 1919536 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3414. Min Act: -0.1700

Data Index: 8157840 (Open Web Text)

Max Activating Token Index: 356

Text #9

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3439. Min Act: -0.1700

Data Index: 3033280 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3697. Min Act: -0.1700

Data Index: 1162312 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3296. Min Act: -0.1700

Data Index: 6809580 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3295. Min Act: -0.1700

Data Index: 2335991 (Open Web Text)

Max Activating Token Index: 376

Text #13

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3343. Min Act: -0.1700

Data Index: 298540 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2926. Min Act: -0.1700

Data Index: 7219477 (Open Web Text)

Max Activating Token Index: 900

Text #15

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3102. Min Act: -0.1700

Data Index: 5356236 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2986. Min Act: -0.1700

Data Index: 5687228 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3092. Min Act: -0.1700

Data Index: 3688866 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.3044. Min Act: -0.1700

Data Index: 5977301 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 3.4324. Min Range: -3.4324

Max Act: 3.2815. Min Act: -0.1700

Data Index: 3717723 (Open Web Text)

Max Activating Token Index: 661