Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0012. Min Range: -6.0012
Max Act: 6.0012. Min Act: -0.1700
Data Index: 8307357 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.9387. Min Act: -0.1700
Data Index: 1006609 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.9074. Min Act: -0.1700
Data Index: 7352935 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.8137. Min Act: -0.1700
Data Index: 1589310 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.7512. Min Act: -0.1700
Data Index: 577335 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.7199. Min Act: -0.1700
Data Index: 5212565 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6887. Min Act: -0.1700
Data Index: 4154944 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6574. Min Act: -0.1700
Data Index: 3809610 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6574. Min Act: -0.1700
Data Index: 2008034 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6887. Min Act: -0.1700
Data Index: 8701493 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6574. Min Act: -0.1700
Data Index: 7646799 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7102194 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.6262. Min Act: -0.1700
Data Index: 1470920 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 1715826 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5949. Min Act: -0.1700
Data Index: 49285 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 553780 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 625096 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 8693456 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 6554378 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0012. Min Range: -6.0012
Max Act: 5.5637. Min Act: -0.1700
Data Index: 3358344 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19