Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.2604. Min Act: -0.1700
Data Index: 4357639 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.1354. Min Act: -0.1700
Data Index: 5464435 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0729. Min Act: -0.1700
Data Index: 2373887 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0104. Min Act: -0.1700
Data Index: 4051783 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4357640 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0104. Min Act: -0.1700
Data Index: 6027177 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0104. Min Act: -0.1700
Data Index: 7816111 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.9479. Min Act: -0.1700
Data Index: 1490379 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.9791. Min Act: -0.1700
Data Index: 4357645 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8854. Min Act: -0.1700
Data Index: 1820836 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8854. Min Act: -0.1700
Data Index: 7177713 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.9166. Min Act: -0.1700
Data Index: 4884338 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8541. Min Act: -0.1700
Data Index: 234352 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8229. Min Act: -0.1700
Data Index: 3583860 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8541. Min Act: -0.1700
Data Index: 3140670 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8541. Min Act: -0.1700
Data Index: 1740090 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8541. Min Act: -0.1700
Data Index: 8010868 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8229. Min Act: -0.1700
Data Index: 2583787 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7916. Min Act: -0.1700
Data Index: 6706018 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7916. Min Act: -0.1700
Data Index: 2804771 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19