Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.1892. Min Act: -0.1700
Data Index: 6840651 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.1580. Min Act: -0.1700
Data Index: 5022360 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.1267. Min Act: -0.1700
Data Index: 8607577 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.0955. Min Act: -0.1700
Data Index: 7362713 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.0642. Min Act: -0.1700
Data Index: 7877573 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.0330. Min Act: -0.1700
Data Index: 4920388 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1892. Min Range: -5.1892
Max Act: 5.0017. Min Act: -0.1700
Data Index: 6531705 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.9705. Min Act: -0.1700
Data Index: 108914 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.9705. Min Act: -0.1700
Data Index: 3284369 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.9705. Min Act: -0.1700
Data Index: 2720591 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6196270 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 3619697 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 8298011 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.9080. Min Act: -0.1700
Data Index: 327095 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6400183 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8767. Min Act: -0.1700
Data Index: 7283713 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8142. Min Act: -0.1700
Data Index: 7479949 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8142. Min Act: -0.1700
Data Index: 6840653 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8142. Min Act: -0.1700
Data Index: 8283279 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1892. Min Range: -5.1892
Max Act: 4.8142. Min Act: -0.1700
Data Index: 6056869 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19