Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3738. Min Range: -10.3738
Max Act: 10.3738. Min Act: -0.1700
Data Index: 6737291 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.8738. Min Act: -0.1700
Data Index: 8703659 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.6238. Min Act: -0.1700
Data Index: 7066779 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.5613. Min Act: -0.1700
Data Index: 5024688 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.4988. Min Act: -0.1700
Data Index: 5545747 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.4988. Min Act: -0.1700
Data Index: 8121165 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.4988. Min Act: -0.1700
Data Index: 1518562 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.3738. Min Act: -0.1700
Data Index: 7732071 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.3738. Min Act: -0.1700
Data Index: 4898233 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.2488. Min Act: -0.1700
Data Index: 2554455 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.3113. Min Act: -0.1699
Data Index: 7529106 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.3113. Min Act: -0.1700
Data Index: 2573457 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.2488. Min Act: -0.1700
Data Index: 6925642 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.2488. Min Act: -0.1700
Data Index: 1187887 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.0613. Min Act: -0.1700
Data Index: 4444327 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.1238. Min Act: -0.1700
Data Index: 2780949 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.0613. Min Act: -0.1700
Data Index: 1224809 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.0613. Min Act: -0.1700
Data Index: 543661 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.0613. Min Act: -0.1700
Data Index: 796437 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3738. Min Range: -10.3738
Max Act: 9.0613. Min Act: -0.1700
Data Index: 345182 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19