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

Dataset: Open Web Text

Neuron 1534 in Layer 2

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: 3.4685. Min Range: -3.4685

Max Act: 3.4685. Min Act: -0.1700

Data Index: 5888861 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3809. Min Act: -0.1700

Data Index: 7393755 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3595. Min Act: -0.1700

Data Index: 6896516 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3278. Min Act: -0.1700

Data Index: 2360004 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3665. Min Act: -0.1700

Data Index: 1762161 (Open Web Text)

Max Activating Token Index: 258

Text #5

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3390. Min Act: -0.1700

Data Index: 314145 (Open Web Text)

Max Activating Token Index: 975

Text #6

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3594. Min Act: -0.1700

Data Index: 8228359 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3175. Min Act: -0.1700

Data Index: 7899521 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3612. Min Act: -0.1700

Data Index: 4478524 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3129. Min Act: -0.1700

Data Index: 6034446 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3394. Min Act: -0.1700

Data Index: 4503467 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3238. Min Act: -0.1700

Data Index: 1626182 (Open Web Text)

Max Activating Token Index: 698

Text #12

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3135. Min Act: -0.1700

Data Index: 7471410 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3016. Min Act: -0.1700

Data Index: 1985518 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3272. Min Act: -0.1700

Data Index: 2491776 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.2997. Min Act: -0.1700

Data Index: 7547449 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.2737. Min Act: -0.1700

Data Index: 1556559 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.2957. Min Act: -0.1700

Data Index: 6574306 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.2733. Min Act: -0.1700

Data Index: 5788422 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 3.4685. Min Range: -3.4685

Max Act: 3.3139. Min Act: -0.1700

Data Index: 2434648 (Open Web Text)

Max Activating Token Index: 707