Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.6622. Min Act: -0.1700
Data Index: 5333252 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.2560. Min Act: -0.1700
Data Index: 6983239 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.2560. Min Act: -0.1700
Data Index: 3334430 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.1622. Min Act: -0.1700
Data Index: 3762685 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.1310. Min Act: -0.1700
Data Index: 2191039 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0997. Min Act: -0.1700
Data Index: 1630181 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0685. Min Act: -0.1700
Data Index: 2091738 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0372. Min Act: -0.1700
Data Index: 3638134 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0372. Min Act: -0.1700
Data Index: 3077423 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0060. Min Act: -0.1700
Data Index: 8039599 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0372. Min Act: -0.1700
Data Index: 8042374 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9747. Min Act: -0.1700
Data Index: 2119763 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0060. Min Act: -0.1700
Data Index: 250648 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0060. Min Act: -0.1700
Data Index: 2138313 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6622. Min Range: -5.6622
Max Act: 5.0060. Min Act: -0.1700
Data Index: 910386 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 7961822 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9747. Min Act: -0.1700
Data Index: 1688024 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9747. Min Act: -0.1700
Data Index: 513135 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4069777 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6622. Min Range: -5.6622
Max Act: 4.9122. Min Act: -0.1700
Data Index: 944233 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19