Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2117 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.9576. Min Act: -0.1700
Data Index: 7580139 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.5201. Min Act: -0.1700
Data Index: 4956735 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.3326. Min Act: -0.1700
Data Index: 479879 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.2389. Min Act: -0.1700
Data Index: 4801206 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1764. Min Act: -0.1700
Data Index: 2881765 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1451. Min Act: -0.1700
Data Index: 6666249 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1451. Min Act: -0.1700
Data Index: 5559570 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1451. Min Act: -0.1700
Data Index: 3210201 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1451. Min Act: -0.1700
Data Index: 443184 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.1139. Min Act: -0.1700
Data Index: 3186080 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.0826. Min Act: -0.1700
Data Index: 1234440 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.0514. Min Act: -0.1700
Data Index: 6567738 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9576. Min Range: -8.9576
Max Act: 8.0201. Min Act: -0.1700
Data Index: 6519408 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9576. Min Act: -0.1700
Data Index: 2138390 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9889. Min Act: -0.1700
Data Index: 5221228 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9889. Min Act: -0.1700
Data Index: 4286841 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9889. Min Act: -0.1700
Data Index: 2633256 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9576. Min Act: -0.1700
Data Index: 3952462 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9264. Min Act: -0.1700
Data Index: 1237445 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9576. Min Range: -8.9576
Max Act: 7.9576. Min Act: -0.1700
Data Index: 3605524 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19