Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.5952. Min Act: -0.1700
Data Index: 4366160 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.4389. Min Act: -0.1700
Data Index: 1541447 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.4389. Min Act: -0.1700
Data Index: 515480 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3764. Min Act: -0.1700
Data Index: 6740766 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3764. Min Act: -0.1700
Data Index: 1442227 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3452. Min Act: -0.1700
Data Index: 6281109 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3139. Min Act: -0.1700
Data Index: 6351086 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3139. Min Act: -0.1700
Data Index: 8162987 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3139. Min Act: -0.1700
Data Index: 6153406 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2827. Min Act: -0.1700
Data Index: 3107500 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.3139. Min Act: -0.1700
Data Index: 5298092 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2514. Min Act: -0.1700
Data Index: 5554531 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2514. Min Act: -0.1700
Data Index: 6918941 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2514. Min Act: -0.1700
Data Index: 5136264 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2764312 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2514. Min Act: -0.1700
Data Index: 4020086 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2202. Min Act: -0.1700
Data Index: 5705400 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2202. Min Act: -0.1700
Data Index: 5610938 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2202. Min Act: -0.1700
Data Index: 600978 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5952. Min Range: -5.5952
Max Act: 5.2202. Min Act: -0.1700
Data Index: 4192007 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19