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

Dataset: Open Web Text

Neuron 958 in Layer 5

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: 3.4905. Min Range: -3.4905

Max Act: 3.4905. Min Act: -0.1700

Data Index: 3138175 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.4061. Min Act: -0.1700

Data Index: 5453382 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.3040. Min Act: -0.1700

Data Index: 3364296 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2952. Min Act: -0.1700

Data Index: 1146044 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2913. Min Act: -0.1700

Data Index: 3755082 (Open Web Text)

Max Activating Token Index: 485

Text #5

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2169. Min Act: -0.1700

Data Index: 3445825 (Open Web Text)

Max Activating Token Index: 404

Text #6

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2173. Min Act: -0.1700

Data Index: 4799195 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2141. Min Act: -0.1700

Data Index: 2958291 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.2073. Min Act: -0.1700

Data Index: 6134665 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1724. Min Act: -0.1700

Data Index: 2380188 (Open Web Text)

Max Activating Token Index: 802

Text #10

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1466. Min Act: -0.1700

Data Index: 2181272 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1486. Min Act: -0.1700

Data Index: 5219370 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1243. Min Act: -0.1700

Data Index: 7661116 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1306. Min Act: -0.1700

Data Index: 4964065 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1307. Min Act: -0.1700

Data Index: 2529840 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1221. Min Act: -0.1700

Data Index: 1539782 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1275. Min Act: -0.1700

Data Index: 7855853 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.0993. Min Act: -0.1700

Data Index: 5220504 (Open Web Text)

Max Activating Token Index: 936

Text #18

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.1088. Min Act: -0.1700

Data Index: 4554140 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.4905. Min Range: -3.4905

Max Act: 3.0863. Min Act: -0.1700

Data Index: 2796815 (Open Web Text)

Max Activating Token Index: 516