Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6165 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3593. Min Range: -4.3593
Max Act: 4.3593. Min Act: -0.1700
Data Index: 10959 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3593. Min Range: -4.3593
Max Act: 4.0155. Min Act: -0.1700
Data Index: 4442668 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3593. Min Range: -4.3593
Max Act: 4.0467. Min Act: -0.1700
Data Index: 97628 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3593. Min Range: -4.3593
Max Act: 4.0467. Min Act: -0.1700
Data Index: 1040189 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3593. Min Range: -4.3593
Max Act: 4.0467. Min Act: -0.1700
Data Index: 2339812 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.9530. Min Act: -0.1700
Data Index: 5395607 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.9217. Min Act: -0.1700
Data Index: 8765728 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.9217. Min Act: -0.1700
Data Index: 5604565 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.9217. Min Act: -0.1700
Data Index: 1996396 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8904. Min Act: -0.1700
Data Index: 5423616 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8904. Min Act: -0.1700
Data Index: 3540951 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8904. Min Act: -0.1700
Data Index: 6041063 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.9217. Min Act: -0.1700
Data Index: 6363218 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8592. Min Act: -0.1700
Data Index: 1310501 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8435. Min Act: -0.1700
Data Index: 832272 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8435. Min Act: -0.1700
Data Index: 813625 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8592. Min Act: -0.1700
Data Index: 1413043 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8592. Min Act: -0.1700
Data Index: 519841 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8279. Min Act: -0.1700
Data Index: 8491389 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3593. Min Range: -4.3593
Max Act: 3.8279. Min Act: -0.1700
Data Index: 6755379 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19