Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5436. Min Act: -0.1700
Data Index: 2570114 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3712. Min Act: -0.1700
Data Index: 7257068 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.2142. Min Act: -0.1700
Data Index: 7551202 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1828. Min Act: -0.1700
Data Index: 1751589 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1670. Min Act: -0.1700
Data Index: 4094923 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1355. Min Act: -0.1700
Data Index: 33063 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1513. Min Act: -0.1700
Data Index: 2131091 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1513. Min Act: -0.1700
Data Index: 241032 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1040. Min Act: -0.1700
Data Index: 4566456 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.1040. Min Act: -0.1700
Data Index: 7697535 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0410. Min Act: -0.1700
Data Index: 491594 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0883. Min Act: -0.1700
Data Index: 2596163 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0725. Min Act: -0.1700
Data Index: 5640226 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0725. Min Act: -0.1700
Data Index: 3306163 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0410. Min Act: -0.1700
Data Index: 4927234 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0252. Min Act: -0.1700
Data Index: 2430226 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0252. Min Act: -0.1700
Data Index: 2417275 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0252. Min Act: -0.1700
Data Index: 1094386 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0094. Min Act: -0.1700
Data Index: 112323 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.0252. Min Act: -0.1700
Data Index: 3257861 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19