Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.7564. Min Act: -0.1700
Data Index: 1743446 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.5377. Min Act: -0.1700
Data Index: 5984657 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4752. Min Act: -0.1700
Data Index: 7761813 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4752. Min Act: -0.1700
Data Index: 3321882 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4439. Min Act: -0.1700
Data Index: 5987037 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4439. Min Act: -0.1700
Data Index: 2974622 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4439. Min Act: -0.1700
Data Index: 5424474 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4439. Min Act: -0.1700
Data Index: 8417773 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4127. Min Act: -0.1700
Data Index: 7085119 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.4127. Min Act: -0.1700
Data Index: 1634239 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7467663 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3502. Min Act: -0.1700
Data Index: 2704529 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3502. Min Act: -0.1700
Data Index: 744420 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3502. Min Act: -0.1700
Data Index: 8232520 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3502. Min Act: -0.1700
Data Index: 4317740 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3502. Min Act: -0.1700
Data Index: 8716449 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3189. Min Act: -0.1700
Data Index: 6618302 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.2877. Min Act: -0.1700
Data Index: 2495237 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.3189. Min Act: -0.1700
Data Index: 8506756 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7564. Min Range: -5.7564
Max Act: 5.2564. Min Act: -0.1700
Data Index: 2437354 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19