Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1418 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1491. Min Range: -6.1491
Max Act: 6.1491. Min Act: -0.1700
Data Index: 6792789 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1491. Min Range: -6.1491
Max Act: 6.0553. Min Act: -0.1693
Data Index: 7942962 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.9928. Min Act: -0.1695
Data Index: 5462745 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.8991. Min Act: -0.1700
Data Index: 1288741 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.8053. Min Act: -0.1700
Data Index: 2867375 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.8053. Min Act: -0.1656
Data Index: 4744292 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.8053. Min Act: -0.1700
Data Index: 4129079 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7741. Min Act: -0.1700
Data Index: 5533141 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7428. Min Act: -0.1700
Data Index: 550502 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7428. Min Act: -0.1699
Data Index: 5441455 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7428. Min Act: -0.1700
Data Index: 3405625 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7116. Min Act: -0.1700
Data Index: 550501 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.7116. Min Act: -0.1700
Data Index: 4748821 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6803. Min Act: -0.1700
Data Index: 249336 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6491. Min Act: -0.1660
Data Index: 5789427 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6491. Min Act: -0.1700
Data Index: 6966935 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6491. Min Act: -0.1700
Data Index: 3874884 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6491. Min Act: -0.1700
Data Index: 3096476 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6178. Min Act: -0.1700
Data Index: 1788385 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1491. Min Range: -6.1491
Max Act: 5.6178. Min Act: -0.1700
Data Index: 7462071 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19