Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.3696. Min Act: -0.1700
Data Index: 8584080 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1969. Min Act: -0.1700
Data Index: 8013970 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1811. Min Act: -0.1700
Data Index: 6748758 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1811. Min Act: -0.1700
Data Index: 367051 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1497. Min Act: -0.1700
Data Index: 5722966 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1497. Min Act: -0.1700
Data Index: 6759336 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1654. Min Act: -0.1700
Data Index: 1408152 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1497. Min Act: -0.1700
Data Index: 5503694 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1497. Min Act: -0.1700
Data Index: 2240471 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1182. Min Act: -0.1700
Data Index: 7721799 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1182. Min Act: -0.1700
Data Index: 6787119 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1182. Min Act: -0.1700
Data Index: 7175593 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.1024. Min Act: -0.1700
Data Index: 5622426 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0866. Min Act: -0.1700
Data Index: 1536470 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0866. Min Act: -0.1700
Data Index: 933237 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0709. Min Act: -0.1700
Data Index: 4042335 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0709. Min Act: -0.1700
Data Index: 3564909 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0551. Min Act: -0.1700
Data Index: 5326210 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0709. Min Act: -0.1700
Data Index: 233323 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3696. Min Range: -3.3696
Max Act: 3.0551. Min Act: -0.1700
Data Index: 8523817 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19