Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4456 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2699. Min Range: -7.2699
Max Act: 7.2699. Min Act: -0.1700
Data Index: 1151394 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.9887. Min Act: -0.1700
Data Index: 3237004 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.9574. Min Act: -0.1700
Data Index: 880500 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.8949. Min Act: -0.1700
Data Index: 3531822 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.8949. Min Act: -0.1700
Data Index: 8239529 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.8324. Min Act: -0.1700
Data Index: 2158523 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.8012. Min Act: -0.1700
Data Index: 2030446 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.8012. Min Act: -0.1700
Data Index: 4821903 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.7699. Min Act: -0.1700
Data Index: 6907293 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.7699. Min Act: -0.1700
Data Index: 3303752 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.7699. Min Act: -0.1700
Data Index: 1154010 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.7387. Min Act: -0.1700
Data Index: 3911089 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.7074. Min Act: -0.1700
Data Index: 814049 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6762. Min Act: -0.1700
Data Index: 8501923 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6449. Min Act: -0.1700
Data Index: 7542182 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6762. Min Act: -0.1700
Data Index: 1749329 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6449. Min Act: -0.1700
Data Index: 1749319 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1554373 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6449. Min Act: -0.1700
Data Index: 759089 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2699. Min Range: -7.2699
Max Act: 6.6449. Min Act: -0.1700
Data Index: 6481748 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19