Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0015. Min Range: -6.0015
Max Act: 6.0015. Min Act: -0.1700
Data Index: 53338 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.9390. Min Act: -0.1700
Data Index: 4221312 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.7827. Min Act: -0.1700
Data Index: 3316890 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.7202. Min Act: -0.1700
Data Index: 8140156 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.6890. Min Act: -0.1700
Data Index: 2028535 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.6577. Min Act: -0.1700
Data Index: 5528892 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.6265. Min Act: -0.1700
Data Index: 4508692 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5952. Min Act: -0.1700
Data Index: 5190811 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5952. Min Act: -0.1700
Data Index: 6934963 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5952. Min Act: -0.1700
Data Index: 920166 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5640. Min Act: -0.1700
Data Index: 210619 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5327. Min Act: -0.1700
Data Index: 5200647 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5015. Min Act: -0.1700
Data Index: 3726459 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5015. Min Act: -0.1700
Data Index: 3299727 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6497325 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.4702. Min Act: -0.1700
Data Index: 8766360 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.4390. Min Act: -0.1700
Data Index: 564387 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6037141 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.4077. Min Act: -0.1700
Data Index: 6584188 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0015. Min Range: -6.0015
Max Act: 5.4077. Min Act: -0.1700
Data Index: 7001236 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19