Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.8910. Min Act: -0.1700
Data Index: 7954757 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.8285. Min Act: -0.1700
Data Index: 5528683 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.6410. Min Act: -0.1700
Data Index: 6140596 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.5785. Min Act: -0.1700
Data Index: 4836302 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.5160. Min Act: -0.1700
Data Index: 5595626 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.5160. Min Act: -0.1700
Data Index: 7581326 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.4535. Min Act: -0.1700
Data Index: 2655174 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.4535. Min Act: -0.1700
Data Index: 8236202 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.3285. Min Act: -0.1700
Data Index: 7409712 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.2660. Min Act: -0.1700
Data Index: 7402051 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.2035. Min Act: -0.1700
Data Index: 4007098 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1098. Min Act: -0.1700
Data Index: 1234548 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1410. Min Act: -0.1700
Data Index: 6040209 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1723. Min Act: -0.1700
Data Index: 6173732 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1410. Min Act: -0.1700
Data Index: 1937454 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1410. Min Act: -0.1700
Data Index: 1134216 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1410. Min Act: -0.1700
Data Index: 4817198 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1098. Min Act: -0.1700
Data Index: 3679628 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1098. Min Act: -0.1700
Data Index: 4249201 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8910. Min Range: -8.8910
Max Act: 8.1098. Min Act: -0.1700
Data Index: 1394994 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19