Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2848. Min Range: -8.2848
Max Act: 8.2848. Min Act: -0.1700
Data Index: 1831118 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2848. Min Range: -8.2848
Max Act: 8.2223. Min Act: -0.1700
Data Index: 5656578 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2848. Min Range: -8.2848
Max Act: 8.2223. Min Act: -0.1700
Data Index: 1831119 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2848. Min Range: -8.2848
Max Act: 8.0973. Min Act: -0.1700
Data Index: 4442390 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2848. Min Range: -8.2848
Max Act: 8.0348. Min Act: -0.1700
Data Index: 4246823 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.9098. Min Act: -0.1700
Data Index: 800693 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.9723. Min Act: -0.1700
Data Index: 4900204 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.9098. Min Act: -0.1700
Data Index: 6674293 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.9098. Min Act: -0.1700
Data Index: 3862667 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.9098. Min Act: -0.1700
Data Index: 4180445 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.8473. Min Act: -0.1700
Data Index: 4840471 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7848. Min Act: -0.1700
Data Index: 1006546 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.8473. Min Act: -0.1700
Data Index: 764194 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.8473. Min Act: -0.1700
Data Index: 6674294 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7848. Min Act: -0.1700
Data Index: 7496767 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7848. Min Act: -0.1700
Data Index: 8004715 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7848. Min Act: -0.1700
Data Index: 8138082 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7223. Min Act: -0.1700
Data Index: 6452275 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.7223. Min Act: -0.1696
Data Index: 5689820 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2848. Min Range: -8.2848
Max Act: 7.6598. Min Act: -0.1700
Data Index: 8024631 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19