Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.4936. Min Act: -0.1700
Data Index: 75050 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.4624. Min Act: -0.1700
Data Index: 4871031 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.1186. Min Act: -0.1700
Data Index: 1884356 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.1186. Min Act: -0.1700
Data Index: 4871032 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.0561. Min Act: -0.1700
Data Index: 4750536 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.0249. Min Act: -0.1700
Data Index: 330930 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4936. Min Range: -7.4936
Max Act: 7.0249. Min Act: -0.1700
Data Index: 6191412 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.9936. Min Act: -0.1700
Data Index: 5405606 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.9936. Min Act: -0.1700
Data Index: 1884354 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.9311. Min Act: -0.1700
Data Index: 8690973 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8999. Min Act: -0.1700
Data Index: 4300211 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.9311. Min Act: -0.1700
Data Index: 8690972 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8999. Min Act: -0.1700
Data Index: 242 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8999. Min Act: -0.1700
Data Index: 4025722 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.9311. Min Act: -0.1700
Data Index: 7921990 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8999. Min Act: -0.1700
Data Index: 225292 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8686. Min Act: -0.1700
Data Index: 5996721 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8686. Min Act: -0.1700
Data Index: 6266054 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8686. Min Act: -0.1700
Data Index: 6191413 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4936. Min Range: -7.4936
Max Act: 6.8374. Min Act: -0.1700
Data Index: 4995318 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19