Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1328 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.4304. Min Range: -13.4304
Max Act: 13.4304. Min Act: -0.1700
Data Index: 3146864 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.4304. Min Range: -13.4304
Max Act: 12.2429. Min Act: -0.1700
Data Index: 3303633 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.4304. Min Range: -13.4304
Max Act: 12.2429. Min Act: -0.1700
Data Index: 8058933 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.4304. Min Range: -13.4304
Max Act: 12.1179. Min Act: -0.1700
Data Index: 5087615 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.4304. Min Range: -13.4304
Max Act: 12.0554. Min Act: -0.1700
Data Index: 2465109 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.9929. Min Act: -0.1700
Data Index: 8524117 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.9929. Min Act: -0.1700
Data Index: 2544793 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.9304. Min Act: -0.1700
Data Index: 7029932 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.9304. Min Act: -0.1700
Data Index: 2515491 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.7429. Min Act: -0.1700
Data Index: 5966841 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.6804. Min Act: -0.1700
Data Index: 5230858 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.6804. Min Act: -0.1700
Data Index: 628933 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.5554. Min Act: -0.1700
Data Index: 3114950 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.6179. Min Act: -0.1700
Data Index: 8431141 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.6179. Min Act: -0.1700
Data Index: 4188580 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.5554. Min Act: -0.1700
Data Index: 6480645 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.5554. Min Act: -0.1700
Data Index: 8702467 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.5554. Min Act: -0.1700
Data Index: 4679103 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.4304. Min Act: -0.1700
Data Index: 5035534 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.4304. Min Range: -13.4304
Max Act: 11.4929. Min Act: -0.1700
Data Index: 3507218 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19