Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1052 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.2595. Min Act: -0.1700
Data Index: 84432 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.2595. Min Act: -0.1700
Data Index: 1655169 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.1658. Min Act: -0.1700
Data Index: 4963806 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.1345. Min Act: -0.1700
Data Index: 1810740 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2142167 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2595. Min Range: -6.2595
Max Act: 6.0720. Min Act: -0.1700
Data Index: 7088611 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9783. Min Act: -0.1700
Data Index: 1373151 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9783. Min Act: -0.1700
Data Index: 5744838 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9783. Min Act: -0.1700
Data Index: 7031452 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9470. Min Act: -0.1700
Data Index: 2998527 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9470. Min Act: -0.1700
Data Index: 1393069 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9470. Min Act: -0.1700
Data Index: 3254773 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5885069 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9158. Min Act: -0.1700
Data Index: 391629 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9158. Min Act: -0.1700
Data Index: 165671 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5541446 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.8533. Min Act: -0.1700
Data Index: 8325191 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.8845. Min Act: -0.1700
Data Index: 8594901 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.8220. Min Act: -0.1700
Data Index: 2241453 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2595. Min Range: -6.2595
Max Act: 5.7908. Min Act: -0.1700
Data Index: 1936119 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19