Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5304 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.4870. Min Act: -0.1700
Data Index: 715363 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.2370. Min Act: -0.1700
Data Index: 1718694 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.2057. Min Act: -0.1700
Data Index: 185560 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.1432. Min Act: -0.1700
Data Index: 8402630 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.1120. Min Act: -0.1700
Data Index: 7821422 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.1120. Min Act: -0.1700
Data Index: 517013 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.0495. Min Act: -0.1700
Data Index: 1302987 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.0182. Min Act: -0.1700
Data Index: 5237619 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.0182. Min Act: -0.1700
Data Index: 4699507 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4870. Min Range: -6.4870
Max Act: 6.0182. Min Act: -0.1700
Data Index: 7301811 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9870. Min Act: -0.1700
Data Index: 4874203 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9870. Min Act: -0.1700
Data Index: 8123223 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9245. Min Act: -0.1700
Data Index: 328645 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9245. Min Act: -0.1700
Data Index: 7046465 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4577923 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9245. Min Act: -0.1700
Data Index: 2604373 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.9245. Min Act: -0.1700
Data Index: 7587681 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.8932. Min Act: -0.1700
Data Index: 8466070 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.8932. Min Act: -0.1700
Data Index: 2562560 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4870. Min Range: -6.4870
Max Act: 5.8620. Min Act: -0.1700
Data Index: 3304636 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19