Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0584. Min Range: -5.0584
Max Act: 5.0584. Min Act: -0.1700
Data Index: 214825 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.9334. Min Act: -0.1700
Data Index: 8750910 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.9021. Min Act: -0.1700
Data Index: 4645256 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.8709. Min Act: -0.1700
Data Index: 1894810 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.8396. Min Act: -0.1700
Data Index: 6858810 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.8084. Min Act: -0.1700
Data Index: 5810363 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.8084. Min Act: -0.1700
Data Index: 7233397 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.8084. Min Act: -0.1700
Data Index: 214899 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7771. Min Act: -0.1700
Data Index: 743715 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7771. Min Act: -0.1700
Data Index: 1025038 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7771. Min Act: -0.1700
Data Index: 6409024 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7771. Min Act: -0.1700
Data Index: 4548302 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7146. Min Act: -0.1700
Data Index: 1687625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7459. Min Act: -0.1700
Data Index: 1471003 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7771. Min Act: -0.1700
Data Index: 795633 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7459. Min Act: -0.1700
Data Index: 7587117 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7459. Min Act: -0.1700
Data Index: 7324714 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7459. Min Act: -0.1700
Data Index: 4925803 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7146. Min Act: -0.1700
Data Index: 1488383 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0584. Min Range: -5.0584
Max Act: 4.7459. Min Act: -0.1700
Data Index: 5633238 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19