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

Dataset: Open Web Text

Neuron 1151 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: 4.6334. Min Range: -4.6334

Max Act: 4.6334. Min Act: -0.1700

Data Index: 5875580 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.6003. Min Act: -0.1700

Data Index: 8593804 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.4547. Min Act: -0.1700

Data Index: 2373869 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.4016. Min Act: -0.1700

Data Index: 2436100 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.4493. Min Act: -0.1700

Data Index: 1505228 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3302. Min Act: -0.1700

Data Index: 7679455 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3424. Min Act: -0.1700

Data Index: 4693582 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3457. Min Act: -0.1700

Data Index: 921499 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3317. Min Act: -0.1700

Data Index: 1469340 (Open Web Text)

Max Activating Token Index: 737

Text #9

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2845. Min Act: -0.1700

Data Index: 2264974 (Open Web Text)

Max Activating Token Index: 480

Text #10

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2942. Min Act: -0.1700

Data Index: 4562515 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3242. Min Act: -0.1700

Data Index: 2755520 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3225. Min Act: -0.1700

Data Index: 8261432 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.3008. Min Act: -0.1700

Data Index: 6033756 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2951. Min Act: -0.1700

Data Index: 770928 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2850. Min Act: -0.1700

Data Index: 3071301 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2915. Min Act: -0.1700

Data Index: 5703203 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2687. Min Act: -0.1700

Data Index: 3249016 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2855. Min Act: -0.1700

Data Index: 3357661 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 4.6334. Min Range: -4.6334

Max Act: 4.2927. Min Act: -0.1700

Data Index: 3496683 (Open Web Text)

Max Activating Token Index: 229