Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0482. Min Range: -6.0482
Max Act: 6.0170. Min Act: -0.1700
Data Index: 148820 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0482. Min Range: -6.0482
Max Act: 6.0482. Min Act: -0.1700
Data Index: 8244494 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9857. Min Act: -0.1700
Data Index: 8439226 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9857. Min Act: -0.1700
Data Index: 1464611 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9545. Min Act: -0.1700
Data Index: 209414 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9232. Min Act: -0.1700
Data Index: 3670382 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9232. Min Act: -0.1700
Data Index: 7319316 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9232. Min Act: -0.1700
Data Index: 7177138 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9232. Min Act: -0.1700
Data Index: 5744432 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8920. Min Act: -0.1700
Data Index: 8793645 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9857. Min Act: -0.1700
Data Index: 4624198 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8920. Min Act: -0.1700
Data Index: 4246340 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8920. Min Act: -0.1700
Data Index: 2209706 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8607. Min Act: -0.1700
Data Index: 8033544 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8607. Min Act: -0.1700
Data Index: 1675549 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8607. Min Act: -0.1700
Data Index: 1405529 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8295. Min Act: -0.1700
Data Index: 5579898 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4158178 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8295. Min Act: -0.1700
Data Index: 5278513 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8295. Min Act: -0.1700
Data Index: 3937102 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19