Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.4761. Min Act: -0.1700
Data Index: 1722412 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.4136. Min Act: -0.1700
Data Index: 3984904 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.4136. Min Act: -0.1700
Data Index: 4965682 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.3511. Min Act: -0.1700
Data Index: 4780416 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.2886. Min Act: -0.1700
Data Index: 4445005 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.2886. Min Act: -0.1700
Data Index: 8430901 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.2261. Min Act: -0.1700
Data Index: 8395663 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.1011. Min Act: -0.1700
Data Index: 1859218 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.1011. Min Act: -0.1700
Data Index: 7739069 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.9761. Min Act: -0.1700
Data Index: 307816 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.1011. Min Act: -0.1700
Data Index: 5204888 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4761. Min Range: -15.4761
Max Act: 15.0386. Min Act: -0.1700
Data Index: 3548222 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.9761. Min Act: -0.1700
Data Index: 513110 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.9761. Min Act: -0.1700
Data Index: 1828333 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.9761. Min Act: -0.1700
Data Index: 3909 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.8511. Min Act: -0.1700
Data Index: 873926 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.9136. Min Act: -0.1700
Data Index: 6350120 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.8511. Min Act: -0.1700
Data Index: 8413765 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.8511. Min Act: -0.1700
Data Index: 8386360 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4761. Min Range: -15.4761
Max Act: 14.8511. Min Act: -0.1700
Data Index: 6600794 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19