Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1994. Min Range: -6.1994
Max Act: 6.1994. Min Act: -0.1700
Data Index: 8825454 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.8869. Min Act: -0.1700
Data Index: 6750062 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7931. Min Act: -0.1700
Data Index: 280075 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7931. Min Act: -0.1700
Data Index: 1723476 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7931. Min Act: -0.1700
Data Index: 555770 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7931. Min Act: -0.1700
Data Index: 2156340 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7931. Min Act: -0.1700
Data Index: 7609308 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.7619. Min Act: -0.1700
Data Index: 6382645 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6994. Min Act: -0.1700
Data Index: 221502 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 1402614 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6994. Min Act: -0.1700
Data Index: 1509782 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6994. Min Act: -0.1700
Data Index: 3472451 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 5793026 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 4091358 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 4216784 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 79197 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 8777156 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 2516164 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 5274568 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1994. Min Range: -6.1994
Max Act: 5.6681. Min Act: -0.1700
Data Index: 1779495 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19