Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0563. Min Range: -10.0563
Max Act: 10.0563. Min Act: -0.1700
Data Index: 8690026 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.9313. Min Act: -0.1700
Data Index: 8806172 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.8688. Min Act: -0.1700
Data Index: 5585012 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.9313. Min Act: -0.1700
Data Index: 2556749 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.8688. Min Act: -0.1700
Data Index: 2556748 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.8063. Min Act: -0.1700
Data Index: 3227825 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6188. Min Act: -0.1700
Data Index: 5246664 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6813. Min Act: -0.1700
Data Index: 8806171 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6813. Min Act: -0.1700
Data Index: 4563450 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6188. Min Act: -0.1700
Data Index: 3660857 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6188. Min Act: -0.1700
Data Index: 987314 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6188. Min Act: -0.1700
Data Index: 7680403 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 5246663 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.6188. Min Act: -0.1700
Data Index: 6129150 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 987315 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 2556750 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 7995839 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 8717526 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 2269014 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0563. Min Range: -10.0563
Max Act: 9.5563. Min Act: -0.1700
Data Index: 3447223 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19