Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.3122. Min Act: -0.1700
Data Index: 5986796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.3122. Min Act: -0.1700
Data Index: 8780708 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.3122. Min Act: -0.1700
Data Index: 6806558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.3122. Min Act: -0.1700
Data Index: 684567 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2809. Min Act: -0.1700
Data Index: 670760 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2497. Min Act: -0.1700
Data Index: 4444497 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2497. Min Act: -0.1700
Data Index: 665905 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2497. Min Act: -0.1700
Data Index: 4678148 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2497. Min Act: -0.1700
Data Index: 167331 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2184. Min Act: -0.1700
Data Index: 2546725 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2184. Min Act: -0.1700
Data Index: 7806341 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2184. Min Act: -0.1700
Data Index: 7737465 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2184. Min Act: -0.1700
Data Index: 6085699 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1559. Min Act: -0.1700
Data Index: 7737464 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1872. Min Act: -0.1700
Data Index: 3301898 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1872. Min Act: -0.1700
Data Index: 2020164 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.2184. Min Act: -0.1700
Data Index: 8702079 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1872. Min Act: -0.1700
Data Index: 5039319 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1872. Min Act: -0.1700
Data Index: 2717483 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3122. Min Range: -5.3122
Max Act: 5.1872. Min Act: -0.1700
Data Index: 3696053 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19