Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.4381. Min Act: -0.1700
Data Index: 6257690 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.3131. Min Act: -0.1700
Data Index: 609786 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.2194. Min Act: -0.1700
Data Index: 2601714 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.2194. Min Act: -0.1700
Data Index: 5197609 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1881. Min Act: -0.1700
Data Index: 3045722 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1881. Min Act: -0.1700
Data Index: 2716504 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 305920 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1881. Min Act: -0.1700
Data Index: 6445131 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1569. Min Act: -0.1700
Data Index: 6585457 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1569. Min Act: -0.1700
Data Index: 4331407 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1569. Min Act: -0.1700
Data Index: 7423340 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1569. Min Act: -0.1700
Data Index: 8544663 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 5197615 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 2136928 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 8725044 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 5638915 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 3982797 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 890199 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.1256. Min Act: -0.1700
Data Index: 7099466 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4381. Min Range: -5.4381
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2860383 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19