Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1029 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.3011. Min Act: -0.1700
Data Index: 8709958 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1136. Min Act: -0.1700
Data Index: 2600645 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1449. Min Act: -0.1700
Data Index: 2546252 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1761. Min Act: -0.1700
Data Index: 4275757 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0824. Min Act: -0.1700
Data Index: 5870114 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0824. Min Act: -0.1700
Data Index: 1871655 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1136. Min Act: -0.1700
Data Index: 2417890 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0199. Min Act: -0.1700
Data Index: 6164319 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0511. Min Act: -0.1700
Data Index: 5837682 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 3206640 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9574. Min Act: -0.1700
Data Index: 7856340 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9574. Min Act: -0.1700
Data Index: 3747445 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9574. Min Act: -0.1700
Data Index: 4230102 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9574. Min Act: -0.1700
Data Index: 329636 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9574. Min Act: -0.1700
Data Index: 328447 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9261. Min Act: -0.1700
Data Index: 2885104 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.8949. Min Act: -0.1700
Data Index: 59073 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.8949. Min Act: -0.1700
Data Index: 742245 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.8636. Min Act: -0.1700
Data Index: 1521584 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.8949. Min Act: -0.1700
Data Index: 7582112 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19