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

Dataset: Open Web Text

Neuron 1599 in Layer 4

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: 2.8601. Min Range: -2.8601

Max Act: 2.8260. Min Act: -0.1700

Data Index: 3312143 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.8601. Min Act: -0.1700

Data Index: 3528846 (Open Web Text)

Max Activating Token Index: 162

Text #2

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.7555. Min Act: -0.1700

Data Index: 5801703 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.7315. Min Act: -0.1700

Data Index: 2436387 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.7188. Min Act: -0.1700

Data Index: 4337212 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.7806. Min Act: -0.1700

Data Index: 2091127 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.7287. Min Act: -0.1700

Data Index: 7689253 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6932. Min Act: -0.1700

Data Index: 6472343 (Open Web Text)

Max Activating Token Index: 81

Text #8

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6769. Min Act: -0.1700

Data Index: 7434770 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6423. Min Act: -0.1700

Data Index: 8449165 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6767. Min Act: -0.1700

Data Index: 3606294 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6845. Min Act: -0.1700

Data Index: 474936 (Open Web Text)

Max Activating Token Index: 722

Text #12

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6658. Min Act: -0.1700

Data Index: 2299585 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6165. Min Act: -0.1700

Data Index: 2130613 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6200. Min Act: -0.1700

Data Index: 1897759 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.6118. Min Act: -0.1700

Data Index: 3081292 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.5867. Min Act: -0.1700

Data Index: 7900876 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.5955. Min Act: -0.1700

Data Index: 6067568 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.5967. Min Act: -0.1700

Data Index: 5738622 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 2.8601. Min Range: -2.8601

Max Act: 2.5969. Min Act: -0.1700

Data Index: 6326505 (Open Web Text)

Max Activating Token Index: 52