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

Dataset: Open Web Text

Neuron 544 in Layer 6

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: 3.2179. Min Range: -3.2179

Max Act: 3.2179. Min Act: -0.1700

Data Index: 4640722 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1898. Min Act: -0.1700

Data Index: 6913582 (Open Web Text)

Max Activating Token Index: 868

Text #2

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.2047. Min Act: -0.1700

Data Index: 780379 (Open Web Text)

Max Activating Token Index: 562

Text #3

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1664. Min Act: -0.1700

Data Index: 8220119 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1489. Min Act: -0.1700

Data Index: 5829512 (Open Web Text)

Max Activating Token Index: 866

Text #5

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1259. Min Act: -0.1700

Data Index: 4265490 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1167. Min Act: -0.1700

Data Index: 5580665 (Open Web Text)

Max Activating Token Index: 769

Text #7

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0923. Min Act: -0.1700

Data Index: 8220120 (Open Web Text)

Max Activating Token Index: 217

Text #8

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1135. Min Act: -0.1700

Data Index: 4013690 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.1005. Min Act: -0.1700

Data Index: 6239943 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0838. Min Act: -0.1700

Data Index: 3337142 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0778. Min Act: -0.1700

Data Index: 902475 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0722. Min Act: -0.1700

Data Index: 2977230 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0648. Min Act: -0.1700

Data Index: 114973 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0814. Min Act: -0.1700

Data Index: 5121203 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0641. Min Act: -0.1700

Data Index: 2819141 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0483. Min Act: -0.1700

Data Index: 1487002 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0527. Min Act: -0.1700

Data Index: 6839856 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0484. Min Act: -0.1700

Data Index: 5134264 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 3.2179. Min Range: -3.2179

Max Act: 3.0739. Min Act: -0.1700

Data Index: 3231397 (Open Web Text)

Max Activating Token Index: 202