Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.4135. Min Act: -0.1700
Data Index: 2368135 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.2260. Min Act: -0.1700
Data Index: 2368134 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1010. Min Act: -0.1700
Data Index: 5088049 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.1323. Min Act: -0.1700
Data Index: 7338179 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 6869023 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 17785 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0698. Min Act: -0.1700
Data Index: 6029290 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0385. Min Act: -0.1700
Data Index: 1418107 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0073. Min Act: -0.1700
Data Index: 17784 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4135. Min Range: -5.4135
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5373622 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.9135. Min Act: -0.1700
Data Index: 1814654 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8823. Min Act: -0.1700
Data Index: 2727600 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8823. Min Act: -0.1700
Data Index: 5563392 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8823. Min Act: -0.1700
Data Index: 8540541 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8823. Min Act: -0.1700
Data Index: 1701278 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8510. Min Act: -0.1700
Data Index: 775516 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8510. Min Act: -0.1700
Data Index: 6428648 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8510. Min Act: -0.1700
Data Index: 180114 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.8198. Min Act: -0.1700
Data Index: 8472349 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4135. Min Range: -5.4135
Max Act: 4.7885. Min Act: -0.1700
Data Index: 8313911 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19