Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6271 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3584. Min Range: -5.3584
Max Act: 5.3584. Min Act: -0.1700
Data Index: 1164938 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3584. Min Range: -5.3584
Max Act: 5.1084. Min Act: -0.1700
Data Index: 737887 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3584. Min Range: -5.3584
Max Act: 5.0459. Min Act: -0.1700
Data Index: 982923 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3584. Min Range: -5.3584
Max Act: 5.0146. Min Act: -0.1700
Data Index: 7490617 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3584. Min Range: -5.3584
Max Act: 5.0146. Min Act: -0.1700
Data Index: 972885 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.9521. Min Act: -0.1700
Data Index: 4415158 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.9521. Min Act: -0.1700
Data Index: 1964889 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.9521. Min Act: -0.1700
Data Index: 1518146 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8896. Min Act: -0.1700
Data Index: 508753 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.9209. Min Act: -0.1700
Data Index: 374801 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.9209. Min Act: -0.1700
Data Index: 2880649 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8896. Min Act: -0.1700
Data Index: 8257190 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8271. Min Act: -0.1700
Data Index: 6193948 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6137917 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7191523 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6686461 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6568415 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8271. Min Act: -0.1700
Data Index: 7191513 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8271. Min Act: -0.1700
Data Index: 5503358 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3584. Min Range: -5.3584
Max Act: 4.8271. Min Act: -0.1700
Data Index: 1980275 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19