Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.2774. Min Act: -0.1700
Data Index: 4374004 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.2461. Min Act: -0.1700
Data Index: 5780503 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.1836. Min Act: -0.1700
Data Index: 5618454 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0899. Min Act: -0.1700
Data Index: 8778141 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.1211. Min Act: -0.1700
Data Index: 7592130 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.1524. Min Act: -0.1700
Data Index: 7592132 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0899. Min Act: -0.1700
Data Index: 3823607 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0899. Min Act: -0.1700
Data Index: 7262273 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0274. Min Act: -0.1700
Data Index: 6516682 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9649. Min Act: -0.1700
Data Index: 7856247 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9649. Min Act: -0.1700
Data Index: 513757 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8711. Min Act: -0.1700
Data Index: 599252 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9024. Min Act: -0.1700
Data Index: 7407293 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9024. Min Act: -0.1700
Data Index: 3924072 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8711. Min Act: -0.1700
Data Index: 5617621 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5615263 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 4653538 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8711. Min Act: -0.1700
Data Index: 8430390 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8711. Min Act: -0.1700
Data Index: 6545860 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8711. Min Act: -0.1700
Data Index: 5284886 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19