Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.4687. Min Act: -0.1700
Data Index: 1148790 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.4374. Min Act: -0.1700
Data Index: 5796012 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.3749. Min Act: -0.1700
Data Index: 5163291 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.3124. Min Act: -0.1700
Data Index: 5646605 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.3124. Min Act: -0.1700
Data Index: 8750404 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.2499. Min Act: -0.1700
Data Index: 452647 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.2187. Min Act: -0.1700
Data Index: 5995942 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.1874. Min Act: -0.1700
Data Index: 7911430 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3410011 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.1562. Min Act: -0.1700
Data Index: 6908107 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.1249. Min Act: -0.1700
Data Index: 850923 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.1249. Min Act: -0.1700
Data Index: 8299207 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0937. Min Act: -0.1700
Data Index: 1631709 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0624. Min Act: -0.1700
Data Index: 6313644 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0624. Min Act: -0.1700
Data Index: 6966787 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0624. Min Act: -0.1700
Data Index: 3051549 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4023900 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0624. Min Act: -0.1700
Data Index: 3235104 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4687. Min Range: -5.4687
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4054316 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4687. Min Range: -5.4687
Max Act: 4.9999. Min Act: -0.1700
Data Index: 7554673 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19