Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1989. Min Range: -5.1989
Max Act: 5.1989. Min Act: -0.1700
Data Index: 3172107 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1989. Min Range: -5.1989
Max Act: 5.1052. Min Act: -0.1700
Data Index: 3944988 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1989. Min Range: -5.1989
Max Act: 5.1052. Min Act: -0.1700
Data Index: 4298843 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1989. Min Range: -5.1989
Max Act: 5.0427. Min Act: -0.1700
Data Index: 434222 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.9802. Min Act: -0.1700
Data Index: 590846 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.8552. Min Act: -0.1700
Data Index: 1989054 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.7614. Min Act: -0.1700
Data Index: 5110791 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.7302. Min Act: -0.1700
Data Index: 7289229 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1563620 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.7614. Min Act: -0.1700
Data Index: 1489021 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.7614. Min Act: -0.1700
Data Index: 4416454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6677. Min Act: -0.1700
Data Index: 4066079 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6547979 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 3827608 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 4882756 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 2793202 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6677. Min Act: -0.1700
Data Index: 5000467 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6677. Min Act: -0.1700
Data Index: 5592221 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6677. Min Act: -0.1700
Data Index: 7199409 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1989. Min Range: -5.1989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 7214268 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19