Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.2609. Min Act: -0.1700
Data Index: 4928343 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1672. Min Act: -0.1700
Data Index: 2553381 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1359. Min Act: -0.1700
Data Index: 2848815 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1047. Min Act: -0.1700
Data Index: 2259284 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1047. Min Act: -0.1700
Data Index: 3114917 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1359. Min Act: -0.1700
Data Index: 447464 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.1047. Min Act: -0.1700
Data Index: 5236065 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0734. Min Act: -0.1700
Data Index: 6237585 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0109. Min Act: -0.1700
Data Index: 737448 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0109. Min Act: -0.1700
Data Index: 2957295 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0109. Min Act: -0.1700
Data Index: 3687627 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0109. Min Act: -0.1700
Data Index: 2419587 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2609. Min Range: -5.2609
Max Act: 5.0109. Min Act: -0.1700
Data Index: 6570300 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9797. Min Act: -0.1700
Data Index: 7569391 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9484. Min Act: -0.1700
Data Index: 626985 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9797. Min Act: -0.1700
Data Index: 1559428 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9484. Min Act: -0.1700
Data Index: 2723159 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9484. Min Act: -0.1700
Data Index: 6226414 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9484. Min Act: -0.1700
Data Index: 5250902 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2609. Min Range: -5.2609
Max Act: 4.9172. Min Act: -0.1700
Data Index: 6018050 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19