Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7229. Min Range: -9.7229
Max Act: 9.7229. Min Act: -0.1700
Data Index: 4414291 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.9729. Min Act: -0.1700
Data Index: 1392601 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.5979. Min Act: -0.1700
Data Index: 2702545 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.4729. Min Act: -0.1700
Data Index: 5767843 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.4104. Min Act: -0.1700
Data Index: 7253860 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.4104. Min Act: -0.1700
Data Index: 884729 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.3479. Min Act: -0.1700
Data Index: 6419996 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.3479. Min Act: -0.1700
Data Index: 6910960 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.2854. Min Act: -0.1700
Data Index: 5561088 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.2229. Min Act: -0.1700
Data Index: 5650778 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.2229. Min Act: -0.1700
Data Index: 8684315 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.2229. Min Act: -0.1700
Data Index: 6149350 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 4037000 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 8608118 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 3957923 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 1247608 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 788623 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.1604. Min Act: -0.1700
Data Index: 8173363 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.0979. Min Act: -0.1700
Data Index: 7569288 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7229. Min Range: -9.7229
Max Act: 8.0979. Min Act: -0.1700
Data Index: 467934 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19