Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.5750. Min Act: -0.1700
Data Index: 2810533 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.1688. Min Act: -0.1700
Data Index: 600940 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.0750. Min Act: -0.1700
Data Index: 3421890 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.0750. Min Act: -0.1700
Data Index: 381298 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.0438. Min Act: -0.1700
Data Index: 6999311 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.0438. Min Act: -0.1700
Data Index: 2836254 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5750. Min Range: -6.5750
Max Act: 6.0438. Min Act: -0.1700
Data Index: 8148491 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.9813. Min Act: -0.1700
Data Index: 5397520 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.9500. Min Act: -0.1700
Data Index: 6673883 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.9188. Min Act: -0.1700
Data Index: 3177251 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8875. Min Act: -0.1700
Data Index: 4707584 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8875. Min Act: -0.1700
Data Index: 1743213 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8563. Min Act: -0.1700
Data Index: 2831907 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8250. Min Act: -0.1700
Data Index: 7898146 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8563. Min Act: -0.1700
Data Index: 3354962 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1019085 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8250. Min Act: -0.1700
Data Index: 5320328 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8250. Min Act: -0.1700
Data Index: 4427692 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.8250. Min Act: -0.1700
Data Index: 2913265 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5750. Min Range: -6.5750
Max Act: 5.7938. Min Act: -0.1700
Data Index: 3124233 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19