Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.1718. Min Act: -0.1700
Data Index: 4409390 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.1405. Min Act: -0.1700
Data Index: 4684514 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.0468. Min Act: -0.1700
Data Index: 706543 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.9843. Min Act: -0.1700
Data Index: 2835996 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.9843. Min Act: -0.1700
Data Index: 6045923 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.9530. Min Act: -0.1700
Data Index: 5300471 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8905. Min Act: -0.1700
Data Index: 3117624 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8593. Min Act: -0.1700
Data Index: 3459145 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8593. Min Act: -0.1700
Data Index: 3781252 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 1833046 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 7227033 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 1889127 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 480485 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 3938935 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 3729460 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 341559 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7343. Min Act: -0.1700
Data Index: 3154183 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 98859 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7343. Min Act: -0.1700
Data Index: 5378717 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7343. Min Act: -0.1700
Data Index: 4442131 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19