Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.4304. Min Act: -0.1700
Data Index: 173074 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.3679. Min Act: -0.1700
Data Index: 5188759 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.2429. Min Act: -0.1700
Data Index: 8780057 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.1804. Min Act: -0.1700
Data Index: 264490 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.0866. Min Act: -0.1700
Data Index: 854278 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.0554. Min Act: -0.1700
Data Index: 3321559 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.0554. Min Act: -0.1700
Data Index: 2344224 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4304. Min Range: -5.4304
Max Act: 5.0241. Min Act: -0.1700
Data Index: 3831572 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.9929. Min Act: -0.1700
Data Index: 1766283 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.9929. Min Act: -0.1700
Data Index: 863476 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.9616. Min Act: -0.1700
Data Index: 1195559 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.9304. Min Act: -0.1700
Data Index: 6897803 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8991. Min Act: -0.1700
Data Index: 8508135 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8991. Min Act: -0.1700
Data Index: 8045260 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8679. Min Act: -0.1700
Data Index: 4130211 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8679. Min Act: -0.1700
Data Index: 2012328 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8679. Min Act: -0.1700
Data Index: 4460615 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8679. Min Act: -0.1700
Data Index: 4509227 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8366. Min Act: -0.1700
Data Index: 2196584 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4304. Min Range: -5.4304
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4950580 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19