Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.6068. Min Act: -0.1700
Data Index: 3748596 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.6381. Min Act: -0.1700
Data Index: 7511998 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5756. Min Act: -0.1700
Data Index: 3376682 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.6381. Min Act: -0.1700
Data Index: 4974152 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.6068. Min Act: -0.1700
Data Index: 1643386 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5443. Min Act: -0.1700
Data Index: 5309007 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5443. Min Act: -0.1700
Data Index: 774202 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5443. Min Act: -0.1700
Data Index: 4448776 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5443. Min Act: -0.1700
Data Index: 1313070 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 4159633 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5982798 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 43734 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 6497609 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5208127 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1740684 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5131. Min Act: -0.1700
Data Index: 7854375 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.5443. Min Act: -0.1700
Data Index: 5915802 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.4818. Min Act: -0.1700
Data Index: 471352 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.4506. Min Act: -0.1700
Data Index: 7178488 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6381. Min Range: -6.6381
Max Act: 6.4506. Min Act: -0.1700
Data Index: 1001892 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19