Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4932928 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.4613. Min Act: -0.1700
Data Index: 8319655 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.4300. Min Act: -0.1700
Data Index: 5632970 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.4300. Min Act: -0.1700
Data Index: 949505 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.3363. Min Act: -0.1700
Data Index: 7790727 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.3363. Min Act: -0.1700
Data Index: 433821 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.2738. Min Act: -0.1700
Data Index: 8679907 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.2425. Min Act: -0.1700
Data Index: 1700833 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.2113. Min Act: -0.1700
Data Index: 4051137 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.2425. Min Act: -0.1700
Data Index: 4184916 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1800. Min Act: -0.1700
Data Index: 2674388 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1800. Min Act: -0.1700
Data Index: 2226595 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1175. Min Act: -0.1700
Data Index: 4007373 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1488. Min Act: -0.1700
Data Index: 4956785 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1488. Min Act: -0.1700
Data Index: 5425977 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1800. Min Act: -0.1700
Data Index: 8109096 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1800. Min Act: -0.1700
Data Index: 1375590 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.1175. Min Act: -0.1700
Data Index: 755948 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.0863. Min Act: -0.1700
Data Index: 4250319 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7113. Min Range: -6.7113
Max Act: 6.0550. Min Act: -0.1700
Data Index: 2898647 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19