Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.5145. Min Act: -0.1700
Data Index: 2783627 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.4970. Min Act: -0.1700
Data Index: 5002382 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.4618. Min Act: -0.1698
Data Index: 4326509 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.4442. Min Act: -0.1700
Data Index: 2300585 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3738. Min Act: -0.1662
Data Index: 2147630 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3385. Min Act: -0.1700
Data Index: 5452574 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3209. Min Act: -0.1696
Data Index: 7720622 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3209. Min Act: -0.1700
Data Index: 4328463 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3032. Min Act: -0.1700
Data Index: 3460103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3032. Min Act: -0.1700
Data Index: 5028724 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.3209. Min Act: -0.1689
Data Index: 2125140 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2856. Min Act: -0.1700
Data Index: 7403474 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1660
Data Index: 2657454 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1696
Data Index: 4550455 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1700
Data Index: 973558 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1700
Data Index: 2776071 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1698
Data Index: 893766 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1699
Data Index: 1530629 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2679. Min Act: -0.1700
Data Index: 993386 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5145. Min Range: -1.5145
Max Act: 1.2856. Min Act: -0.1697
Data Index: 8709588 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19