Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5676 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3859. Min Range: -6.3859
Max Act: 6.3859. Min Act: -0.1700
Data Index: 6842708 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3859. Min Range: -6.3859
Max Act: 6.2609. Min Act: -0.1700
Data Index: 4320035 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3859. Min Range: -6.3859
Max Act: 6.1046. Min Act: -0.1700
Data Index: 6955266 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3859. Min Range: -6.3859
Max Act: 6.0109. Min Act: -0.1700
Data Index: 6315323 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.9796. Min Act: -0.1700
Data Index: 2265460 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.9484. Min Act: -0.1700
Data Index: 4140733 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8859. Min Act: -0.1700
Data Index: 5630373 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.9171. Min Act: -0.1700
Data Index: 3495965 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.9171. Min Act: -0.1700
Data Index: 7141582 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8859. Min Act: -0.1700
Data Index: 493785 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 8389390 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 336251 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 3386860 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 3462754 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1271215 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8546. Min Act: -0.1700
Data Index: 4915884 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8234. Min Act: -0.1700
Data Index: 1499258 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8234. Min Act: -0.1700
Data Index: 658301 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.8234. Min Act: -0.1700
Data Index: 4017451 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3859. Min Range: -6.3859
Max Act: 5.7921. Min Act: -0.1700
Data Index: 4139057 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19