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

Dataset: Open Web Text

Neuron 428 in Layer 1

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: 2.0088. Min Range: -2.0088

Max Act: 2.0088. Min Act: -0.1700

Data Index: 3952545 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9781. Min Act: -0.1700

Data Index: 8744582 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9276. Min Act: -0.1700

Data Index: 2811591 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9336. Min Act: -0.1700

Data Index: 6303369 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9312. Min Act: -0.1700

Data Index: 5073258 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9321. Min Act: -0.1700

Data Index: 677744 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9311. Min Act: -0.1700

Data Index: 92546 (Open Web Text)

Max Activating Token Index: 905

Text #7

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9308. Min Act: -0.1700

Data Index: 5218130 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9305. Min Act: -0.1700

Data Index: 4199036 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9261. Min Act: -0.1700

Data Index: 8792575 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9194. Min Act: -0.1700

Data Index: 7356200 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9160. Min Act: -0.1700

Data Index: 6761785 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9319. Min Act: -0.1700

Data Index: 6429609 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9161. Min Act: -0.1700

Data Index: 3908948 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.8932. Min Act: -0.1700

Data Index: 1676177 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9046. Min Act: -0.1700

Data Index: 5910418 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9072. Min Act: -0.1700

Data Index: 4111583 (Open Web Text)

Max Activating Token Index: 348

Text #17

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.9068. Min Act: -0.1700

Data Index: 6051121 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.8947. Min Act: -0.1700

Data Index: 383912 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 2.0088. Min Range: -2.0088

Max Act: 1.8988. Min Act: -0.1700

Data Index: 3058292 (Open Web Text)

Max Activating Token Index: 959