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

Dataset: Open Web Text

Neuron 2686 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: 1.7163. Min Range: -1.7163

Max Act: 1.7163. Min Act: -0.1700

Data Index: 4562585 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.7109. Min Act: -0.1700

Data Index: 7434666 (Open Web Text)

Max Activating Token Index: 840

Text #2

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6806. Min Act: -0.1700

Data Index: 1719247 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6692. Min Act: -0.1700

Data Index: 217410 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6572. Min Act: -0.1700

Data Index: 81458 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6373. Min Act: -0.1700

Data Index: 5931912 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6438. Min Act: -0.1699

Data Index: 6981953 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6387. Min Act: -0.1700

Data Index: 7783532 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6285. Min Act: -0.1644

Data Index: 6068431 (Open Web Text)

Max Activating Token Index: 898

Text #9

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6175. Min Act: -0.1700

Data Index: 4753715 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6158. Min Act: -0.1700

Data Index: 81459 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6190. Min Act: -0.1700

Data Index: 4534097 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6043. Min Act: -0.1700

Data Index: 5922436 (Open Web Text)

Max Activating Token Index: 112

Text #13

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6075. Min Act: -0.1699

Data Index: 407594 (Open Web Text)

Max Activating Token Index: 743

Text #14

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6065. Min Act: -0.1700

Data Index: 3806218 (Open Web Text)

Max Activating Token Index: 579

Text #15

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6179. Min Act: -0.1699

Data Index: 6176792 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.5929. Min Act: -0.1700

Data Index: 3038579 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.5936. Min Act: -0.1700

Data Index: 815997 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.5982. Min Act: -0.1700

Data Index: 4399074 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.5957. Min Act: -0.1700

Data Index: 2639875 (Open Web Text)

Max Activating Token Index: 177