Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.5257. Min Act: -0.1700
Data Index: 7350234 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.2132. Min Act: -0.1700
Data Index: 8098974 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.1819. Min Act: -0.1700
Data Index: 2748785 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.1507. Min Act: -0.1700
Data Index: 8260835 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.0882. Min Act: -0.1700
Data Index: 6454325 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.0569. Min Act: -0.1700
Data Index: 7940593 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5883010 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5257. Min Range: -5.5257
Max Act: 5.0257. Min Act: -0.1700
Data Index: 2841584 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.9632. Min Act: -0.1700
Data Index: 6529819 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.9319. Min Act: -0.1700
Data Index: 6985696 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8382. Min Act: -0.1700
Data Index: 4904419 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8694. Min Act: -0.1700
Data Index: 6354915 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8069. Min Act: -0.1700
Data Index: 7468835 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8069. Min Act: -0.1700
Data Index: 1180722 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8069. Min Act: -0.1700
Data Index: 4480832 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.7757. Min Act: -0.1700
Data Index: 4354386 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.7757. Min Act: -0.1700
Data Index: 861209 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.8069. Min Act: -0.1700
Data Index: 4695720 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.7757. Min Act: -0.1700
Data Index: 4714444 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5257. Min Range: -5.5257
Max Act: 4.7757. Min Act: -0.1700
Data Index: 4854032 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19